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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating extreme actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pressed
    -0.15
    ismet
    -0.14
    728
    -0.14
     Ñģобой
    -0.14
     lag
    -0.14
    latex
    -0.14
    egov
    -0.13
    INGER
    -0.13
     пÑĢов
    -0.13
     Noel
    -0.13
    POSITIVE LOGITS
    ornment
    0.17
    ãģ£ãģį
    0.15
    .AUTO
    0.15
    FOX
    0.14
    erno
    0.13
    umbs
    0.13
    ×ķ
    0.13
     ENG
    0.13
    mites
    0.13
    ESH
    0.13
    Act Density 0.132%

    No Known Activations