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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anch
    -0.17
    .partner
    -0.14
    OLEAN
    -0.14
    士
    -0.14
    uche
    -0.14
    avity
    -0.14
    ---</
    -0.14
    ambre
    -0.14
    argo
    -0.14
     fitte
    -0.14
    POSITIVE LOGITS
    s
    0.18
    linger
    0.16
     Whites
    0.15
    sis
    0.15
    /XML
    0.15
     Herbert
    0.14
    scape
    0.14
     Flo
    0.14
     Lo
    0.14
    upp
    0.14
    Act Density 0.164%

    No Known Activations