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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" and its capitalized variant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igshid
    -0.60
    providedIn
    -0.57
    Hochspringen
    -0.57
    aronder
    -0.56
     distanciation
    -0.56
    abestanden
    -0.55
     kveld
    -0.53
     okuyayım
    -0.53
     Banks
    -0.53
    instancetype
    -0.52
    POSITIVE LOGITS
    To
    0.89
    DataTo
    0.88
     TO
    0.84
     To
    0.83
     Toh
    0.83
     προς
    0.80
    TO
    0.79
    to
    0.79
    mapsto
    0.79
    mapTo
    0.72
    Act Density 0.279%

    No Known Activations