© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 918
    Prev
    Next
    INDEX
    Explanations

    terms that denote lack of value or significance

    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
    aneers
    -0.83
     rul
    -0.70
    ells
    -0.69
    oise
    -0.66
    anwhile
    -0.65
    sted
    -0.64
     awa
    -0.63
    estern
    -0.63
    aunder
    -0.62
    arat
    -0.62
    POSITIVE LOGITS
     Solitaire
    0.64
     stranger
    0.62
    ��
    0.62
    ource
    0.62
     interchange
    0.59
     considering
    0.58
    ��
    0.58
    piece
    0.57
     anyway
    0.57
    fork
    0.57
    Activations Density 0.140%

    No Known Activations