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

    Neuronpedia

    INDEX
    Explanations

    the word "is" followed by an adjective

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "I'm" and related phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oner
    -0.77
    alities
    -0.72
    ono
    -0.71
     Presbyter
    -0.70
    lly
    -0.69
     Armen
    -0.69
    bourg
    -0.68
     Must
    -0.67
     Catal
    -0.64
    orate
    -0.64
    POSITIVE LOGITS
    entimes
    0.78
     confronted
    0.77
    erva
    0.70
    roup
    0.68
     downtime
    0.66
     partnered
    0.66
     faced
    0.66
     overrun
    0.65
     gone
    0.64
    IED
    0.64
    Act Density 0.191%

    No Known Activations