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

    Neuronpedia

    INDEX
    Explanations

    instances of bans or restrictions related to individuals or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utes
    -0.17
    chers
    -0.17
    elere
    -0.16
    aversable
    -0.15
    ulong
    -0.15
    ateral
    -0.14
    eldorf
    -0.14
    ingly
    -0.14
    acher
    -0.14
    avirus
    -0.14
    POSITIVE LOGITS
     woman
    0.26
     someone
    0.22
     man
    0.21
     guy
    0.21
     young
    0.21
     couple
    0.19
     girl
    0.18
     person
    0.17
     employee
    0.17
     lady
    0.17
    Act Density 0.244%

    No Known Activations