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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection or positive feelings towards people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.62
    FormTagHelper
    -0.57
    Билгалдахарш
    -0.52
    发表于
    -0.52
    tonode
    -0.52
    তথ্যসূত্র
    -0.50
    CrossRef
    -0.48
     kasarigan
    -0.47
    <_>
    -0.47
    -0.47
    POSITIVE LOGITS
     hearing
    0.62
     watching
    0.60
     surprises
    0.56
     seeing
    0.56
     reading
    0.54
     simplicity
    0.49
     tinkering
    0.48
     spicy
    0.47
     tanken
    0.47
     playing
    0.46
    Act Density 0.182%

    No Known Activations