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

    Neuronpedia

    INDEX
    Explanations

    adjectives implying humility or simplicity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of the word "modest" indicating varying degrees of smallness or restraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emis
    -0.70
    oldown
    -0.69
    AW
    -0.69
    ACTION
    -0.69
    SW
    -0.64
    AMS
    -0.63
     Aval
    -0.62
    onz
    -0.61
    izzard
    -0.60
    avez
    -0.60
    POSITIVE LOGITS
    ly
    1.37
     beginnings
    0.93
     sized
    0.91
     consolation
    0.90
     (<
    0.88
    LY
    0.87
    ally
    0.87
     minded
    0.78
    lys
    0.77
     amounts
    0.77
    Act Density 0.026%

    No Known Activations