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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements and expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Viet
    -0.17
    cth
    -0.16
    dej
    -0.15
    vit
    -0.15
    rippling
    -0.14
    ohen
    -0.14
    jem
    -0.14
     رض
    -0.14
    .AddItem
    -0.14
    _ALLOW
    -0.14
    POSITIVE LOGITS
    ạp
    0.16
    204
    0.15
    038
    0.14
    اÙĬÙĦ
    0.14
    ignum
    0.14
    Sense
    0.14
    olem
    0.14
    aman
    0.14
    ailer
    0.13
     {{--<
    0.13
    Act Density 0.158%

    No Known Activations