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

    Neuronpedia

    INDEX
    Explanations

    words that convey prominence or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikan
    -0.17
    atego
    -0.17
    aho
    -0.17
    paque
    -0.15
    itial
    -0.15
     jadx
    -0.15
    .Scheme
    -0.14
    antan
    -0.14
    deen
    -0.14
    THR
    -0.14
    POSITIVE LOGITS
    éĿ
    0.15
    ewis
    0.15
    /power
    0.14
     MDB
    0.14
     yet
    0.14
     ones
    0.13
    ews
    0.13
     remaining
    0.13
     Possible
    0.13
     cris
    0.13
    Act Density 0.088%

    No Known Activations