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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user consent and agreements

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

    Agreement, consent, or acknowledgment

    np_acts-logits-general · gemini-2.0-flash

    you agree to waive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.68
    Попис
    -0.60
    afficheront
    -0.57
    Geplaatst
    -0.56
     envy
    -0.56
    IFO
    -0.55
     חיצוניים
    -0.55
    IUrlHelper
    -0.55
    Gambas
    -0.55
    HasColumnName
    -0.54
    POSITIVE LOGITS
     agree
    1.33
     agrees
    1.24
    agree
    1.23
     agreeing
    1.20
     Agree
    1.09
    Agree
    0.99
     agreed
    0.95
     acknowledge
    0.94
     acknowledges
    0.90
     acceptance
    0.89
    Act Density 0.447%

    No Known Activations