Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 406
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "der" in various contexts

    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
    antis
    -0.71
     liberties
    -0.70
    anwhile
    -0.69
    justice
    -0.67
    ees
    -0.67
    alian
    -0.65
    ioned
    -0.63
     apprehens
    -0.63
    ilton
    -0.62
    iao
    -0.61
    POSITIVE LOGITS
    ��
    0.74
    pri
    0.67
    ��
    0.66
     Scor
    0.64
    pictured
    0.62
     certs
    0.61
    massive
    0.61
    �
    0.60
    qv
    0.60
     RH
    0.59
    Activations Density 0.017%

    No Known Activations