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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or symbols typically used in written language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bish
    -0.15
     ReturnValue
    -0.14
    lob
    -0.14
     Howell
    -0.14
    cco
    -0.13
     kiá»ĥu
    -0.13
     Singh
    -0.13
    dik
    -0.13
    ucci
    -0.13
    atre
    -0.13
    POSITIVE LOGITS
    pedia
    0.16
    @student
    0.15
     journal
    0.14
    oming
    0.14
    omb
    0.14
    ÃŁe
    0.14
    帽
    0.13
    izza
    0.13
    aded
    0.13
    zym
    0.13
    Act Density 0.002%

    No Known Activations