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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" indicating intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.81
    almaz
    -0.80
    เอง
    -0.74
     Gales
    -0.73
     zijne
    -0.72
    ollection
    -0.72
     gethan
    -0.70
    Komentar
    -0.69
     saisir
    -0.69
     uyt
    -0.69
    POSITIVE LOGITS
    Gotta
    1.08
     gotta
    1.04
     Gotta
    1.00
     must
    0.94
     be
    0.93
    zzleHttp
    0.85
    gotta
    0.77
     needs
    0.76
    icoot
    0.76
    Must
    0.76
    Act Density 0.105%

    No Known Activations