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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that start with a preposition indicating a relationship or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faſt
    -0.69
     raiſ
    -0.66
     itſelf
    -0.63
     pleaſure
    -0.61
     ſtand
    -0.60
     ainfi
    -0.60
     Houſe
    -0.60
     slutt
    -0.59
     ſche
    -0.58
     kasarigan
    -0.58
    POSITIVE LOGITS
     de
    1.23
     of
    0.95
     De
    0.91
     di
    0.88
    De
    0.88
     OF
    0.82
    of
    0.74
     Of
    0.74
     DE
    0.73
    ของ
    0.73
    Act Density 0.082%

    No Known Activations