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

    Neuronpedia

    INDEX
    Explanations

    elements related to academic publication metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UN
    -0.16
    pond
    -0.15
    ([]*
    -0.15
     Tomorrow
    -0.15
     Watts
    -0.15
    Jur
    -0.14
     Manuals
    -0.14
    #region
    -0.14
    Ķ
    -0.14
    asta
    -0.14
    POSITIVE LOGITS
     ACCEPT
    0.23
     Accepted
    0.23
    .Accept
    0.23
     accepted
    0.22
     acceptance
    0.21
    Accepted
    0.21
     acept
    0.20
    oola
    0.20
    accepted
    0.20
     peer
    0.19
    Act Density 0.013%

    No Known Activations