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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "see" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.95
     >=",
    -0.88
    styleType
    -0.82
    )});
    -0.80
    "]];
    -0.80
     Roskov
    -0.76
    abestanden
    -0.75
    MergeFrom
    -0.74
    djangoproject
    -0.74
    "]);
    -0.74
    POSITIVE LOGITS
     saw
    0.77
    saw
    0.72
    見
    0.69
    Saw
    0.68
     Sees
    0.67
    見た
    0.66
     seeing
    0.65
     Saw
    0.65
    Seeing
    0.64
    看
    0.64
    Act Density 0.383%

    No Known Activations