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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional communication and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ごちそうさまでした
    -0.64
    こうした
    -0.62
     variously
    -0.55
    更好地
    -0.54
    一方で
    -0.53
    おわりに
    -0.53
    createCanvas
    -0.50
    これまで
    -0.50
    KURZBESCHREIBUNG
    -0.49
    wiście
    -0.49
    POSITIVE LOGITS
     its
    1.27
     Thats
    1.17
    Its
    1.14
    Thats
    1.12
    its
    1.09
     Its
    1.08
    thats
    1.02
     Dont
    1.01
     thats
    1.01
    Dont
    1.00
    Act Density 0.523%

    No Known Activations