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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Men" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENCY
    -0.78
    ENC
    -0.78
    使
    -0.72
    âĺħâĺħ
    -0.70
    ITED
    -0.69
    Closure
    -0.69
    tainment
    -0.67
    RAY
    -0.67
    WT
    -0.67
    IFT
    -0.64
    POSITIVE LOGITS
    endez
    1.31
    cius
    1.09
    uscript
    1.08
    iscal
    1.06
    opausal
    1.03
    ghai
    1.00
    ager
    0.99
    ogyn
    0.92
    azi
    0.91
    istries
    0.90
    Act Density 0.021%

    No Known Activations