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

    Neuronpedia

    INDEX
    Explanations

    references to local or time-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ('
    -0.16
     Mast
    -0.15
    idge
    -0.15
     radi
    -0.14
    ston
    -0.14
    ilor
    -0.14
     Fu
    -0.14
     Bad
    -0.14
     contribution
    -0.14
     War
    -0.13
    POSITIVE LOGITS
     пÑĢим
    0.17
    ValueCollection
    0.15
    ãĤµãĤ¤
    0.15
    ourn
    0.15
    .Native
    0.15
    vá
    0.14
     âĹĦ
    0.14
    ainter
    0.14
     Helvetica
    0.14
    åªĴ
    0.14
    Act Density 0.070%

    No Known Activations