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

    Neuronpedia

    INDEX
    Explanations

    verbs and terms indicating actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bellev
    -0.16
     Huck
    -0.15
    ern
    -0.14
    PTS
    -0.14
     ÑģÑĤÑĢо
    -0.13
    ActionTypes
    -0.13
    лек
    -0.13
    çĩķ
    -0.13
    Nam
    -0.13
    ожеÑĤ
    -0.13
    POSITIVE LOGITS
    oles
    0.18
    leys
    0.16
    éru
    0.15
    åĨĨ
    0.15
    gart
    0.14
    ogie
    0.14
    IDL
    0.14
    draulic
    0.14
    uhl
    0.14
    ellij
    0.14
    Act Density 0.001%

    No Known Activations