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

    Neuronpedia

    INDEX
    Explanations

    numerical values paired with contextual references or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.63
     also
    -0.59
     оригіналу
    -0.58
    ;
    -0.56
    </b>
    -0.55
    nością
    -0.54
     секунд
    -0.53
    ↵
    -0.52
    ↵↵↵
    -0.51
     también
    -0.51
    POSITIVE LOGITS
    abestanden
    0.95
     Soh
    0.84
    atorze
    0.78
    TagMode
    0.75
    thirty
    0.74
     nakalista
    0.74
    kusen
    0.74
    ASHINGTON
    0.73
    venty
    0.72
    ecute
    0.71
    Act Density 1.240%

    No Known Activations