© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 810
    Prev
    Next
    INDEX
    Explanations

    the use of the word "But" indicating contrast or transition in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stressed
    -0.70
     batted
    -0.68
    ���
    -0.68
    yip
    -0.68
     emphasized
    -0.67
     practiced
    -0.66
    CLUD
    -0.66
    yles
    -0.66
    sburg
    -0.64
    keyes
    -0.64
    POSITIVE LOGITS
     shortly
    0.92
     after
    0.84
     midway
    0.81
     afterwards
    0.74
     when
    0.72
     halfway
    0.72
     sometime
    0.71
     due
    0.69
    ーン
    0.66
     instead
    0.65
    Activations Density 0.130%

    No Known Activations