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

    Neuronpedia

    INDEX
    Explanations

    expressions of deep emotion and gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Modes
    -0.59
    lihood
    -0.58
     affidav
    -0.57
     batter
    -0.57
     assailants
    -0.56
     jurisdiction
    -0.56
     acre
    -0.55
     traces
    -0.54
    saf
    -0.54
     Mong
    -0.54
    POSITIVE LOGITS
    ooo
    1.21
    oooo
    1.19
    othe
    1.19
    bered
    1.17
    apy
    1.08
    oner
    1.06
    oths
    1.05
    othes
    1.04
    arin
    1.02
    ppy
    1.01
    Act Density 0.110%

    No Known Activations