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

    Neuronpedia

    INDEX
    Explanations

    words related to affirmation or agreement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to affirmation or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TOP
    -1.06
    DragonMagazine
    -0.83
    DCS
    -0.82
    TOR
    -0.79
    swick
    -0.79
    REDACTED
    -0.77
    ETF
    -0.76
    Assembly
    -0.75
    HCR
    -0.75
    hou
    -0.74
    POSITIVE LOGITS
     affirmative
    0.99
    irmation
    0.80
     imperative
    0.78
     affirmation
    0.76
     affirm
    0.75
     screening
    0.71
     awakening
    0.70
     Pwr
    0.68
     warr
    0.68
     screenings
    0.67
    Act Density 0.010%

    No Known Activations