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

    Neuronpedia

    INDEX
    Explanations

    words related to driving, medical terms, and names

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itably
    -0.77
    ancial
    -0.76
    ividual
    -0.74
    irlf
    -0.72
    ;;;;;;;;;;;;
    -0.71
    uilt
    -0.70
    escription
    -0.68
    lished
    -0.66
    othal
    -0.64
    mercial
    -0.63
    POSITIVE LOGITS
    CLASSIFIED
    1.00
     behavi
    0.86
    NetMessage
    0.83
    GoldMagikarp
    0.81
    WAYS
    0.81
    Balt
    0.77
     antioxid
    0.75
    natureconservancy
    0.75
     toile
    0.74
     largeDownload
    0.74
    Act Density 6.505%

    No Known Activations