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

    Neuronpedia

    INDEX
    Explanations

    expressions of willingness and agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Expressing agreement or willingness

    np_acts-logits-general · gemini-2.0-flash

    agree or willing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.55
     kasarigan
    -0.50
     bomb
    -0.45
    Graduation
    -0.42
     mask
    -0.40
     navideñas
    -0.40
     zorgen
    -0.39
    Дорогие
    -0.39
     Lebe
    -0.39
    sector
    -0.38
    POSITIVE LOGITS
     accepts
    0.90
     accept
    0.88
    accept
    0.82
    Willing
    0.79
    accepts
    0.79
     accepting
    0.77
     Accepting
    0.75
    willing
    0.74
     accepte
    0.74
     Accept
    0.73
    Act Density 0.435%

    No Known Activations