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

    Neuronpedia

    INDEX
    Explanations

    instances of vision-related verbs in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    initializeApp
    -0.87
    vergne
    -0.82
    ništvo
    -0.82
    enderror
    -0.81
     snippetHide
    -0.80
    ReusableCell
    -0.74
     Bettina
    -0.73
    ergies
    -0.73
    IsContent
    -0.73
     AppColors
    -0.69
    POSITIVE LOGITS
     saw
    0.90
    saw
    0.84
     spotted
    0.74
    Saw
    0.74
     heard
    0.71
     Saw
    0.68
     seen
    0.67
     gezien
    0.66
     noticed
    0.64
     seeing
    0.63
    Act Density 0.190%

    No Known Activations