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

    Neuronpedia

    INDEX
    Explanations

    names associated with certain entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    proper names and specific titles, particularly those related to individuals and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acular
    -0.80
    orative
    -0.79
    owicz
    -0.78
    ications
    -0.78
    orius
    -0.75
    uary
    -0.73
    anguage
    -0.72
    uality
    -0.72
    inyl
    -0.70
    Ô
    -0.70
    POSITIVE LOGITS
     Vive
    0.81
    IGH
    0.77
    ISTORY
    0.77
    ttle
    0.70
    wives
    0.70
    HAHA
    0.69
    Stand
    0.69
    ospital
    0.69
     LF
    0.69
     Hoff
    0.67
    Act Density 0.064%

    No Known Activations