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

    Neuronpedia

    INDEX
    Explanations

    words indicating exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.75
    gonic
    -0.64
    RectangleBorder
    -0.61
     PAM
    -0.53
    dição
    -0.52
     TPS
    -0.51
    PreInfinity
    -0.51
    XO
    -0.51
    PII
    -0.50
     VX
    -0.50
    POSITIVE LOGITS
     barely
    0.66
    SourceChecksum
    0.59
     fewer
    0.59
    短短
    0.59
     little
    0.59
     less
    0.58
    alnız
    0.58
    inver
    0.57
    lccn
    0.57
     scarcely
    0.57
    Act Density 0.033%

    No Known Activations