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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

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

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     deviation
    -0.75
     projecting
    -0.72
     Inferno
    -0.64
     Revision
    -0.64
     Osc
    -0.63
    inese
    -0.63
     conver
    -0.62
    FO
    -0.61
     nerv
    -0.60
    ELF
    -0.60
    POSITIVE LOGITS
    gements
    0.80
    gments
    0.79
    giving
    0.78
     Thank
    0.76
    ickets
    0.72
    ride
    0.71
     Emails
    0.69
    ifully
    0.68
    gment
    0.68
     thanking
    0.67
    Act Density 0.010%

    No Known Activations