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

    Neuronpedia

    INDEX
    Explanations

    words related to technical aspects and activities such as software features and construction tasks

    oai_token-act-pair · gpt-3.5-turbo

    words and prefixes that suggest specific actions or conditions associated with illness or medical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.91
    stellar
    -0.86
     Presbyterian
    -0.74
    FUL
    -0.73
    bush
    -0.66
     Jehovah
    -0.63
     Reincarnated
    -0.62
     Benz
    -0.60
     Continued
    -0.59
     Galile
    -0.59
    POSITIVE LOGITS
    itiz
    1.08
    vers
    1.01
    glers
    0.96
    odes
    0.95
    rors
    0.94
    acts
    0.94
    ancies
    0.93
    arers
    0.93
    iencies
    0.88
    isers
    0.88
    Act Density 0.518%

    No Known Activations