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

    Neuronpedia

    INDEX
    Explanations

    instances of intimate or personal conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XCTest
    -0.53
    curkan
    -0.48
    silien
    -0.48
     option
    -0.48
     tercih
    -0.46
    option
    -0.45
    اله
    -0.45
    tió
    -0.45
     zoeken
    -0.45
     score
    -0.44
    POSITIVE LOGITS
    UrlResolution
    0.86
    extAlignment
    0.78
     EClass
    0.73
     ProtoMessage
    0.71
    AndEndTag
    0.66
    RenderAtEndOf
    0.64
    ьаж
    0.62
    awtextra
    0.62
     @"/
    0.62
     myſelf
    0.61
    Act Density 0.675%

    No Known Activations