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

    Neuronpedia

    INDEX
    Explanations

    symbols or punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.20
    es
    -0.17
    erson
    -0.16
    aul
    -0.15
    iger
    -0.15
    ме
    -0.15
    ror
    -0.15
    wy
    -0.15
    ie
    -0.14
     once
    -0.14
    POSITIVE LOGITS
    ::|
    0.25
     zdrav
    0.20
    abbo
    0.17
    -fontawesome
    0.16
    kop
    0.16
    .scalablytyped
    0.16
    ças
    0.16
    ￣￣￣￣￣￣￣￣
    0.15
    ulaire
    0.15
    Ñİн
    0.15
    Act Density 0.025%

    No Known Activations