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

    Neuronpedia

    INDEX
    Explanations

    words that indicate inquiry or selection in questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -0.58
     Winaray
    -0.56
    .")]
    -0.53
    providedIn
    -0.53
    farwyddwr
    -0.52
     mouseClicked
    -0.52
    '])
    -0.52
    nteral
    -0.52
    volmente
    -0.51
    genheiten
    -0.51
    POSITIVE LOGITS
     whether
    0.67
    spaceBetween
    0.56
     Whether
    0.54
    lccc
    0.52
    Whether
    0.52
     apakah
    0.51
    strategia
    0.51
     how
    0.50
    elemField
    0.49
    errHandler
    0.49
    Act Density 0.413%

    No Known Activations