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

    Neuronpedia

    INDEX
    Explanations

    phrases containing people's names

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interchange
    -0.68
     exha
    -0.65
     fueling
    -0.65
    interstitial
    -0.65
     economies
    -0.63
     outcomes
    -0.63
     encount
    -0.62
     departures
    -0.62
     obser
    -0.61
     remaining
    -0.61
    POSITIVE LOGITS
     huh
    1.03
     Gentleman
    0.88
    hov
    0.87
     thank
    0.81
     please
    0.81
     oh
    0.78
     yeah
    0.75
     beware
    0.75
     Disciple
    0.74
    usalem
    0.73
    Act Density 0.360%

    No Known Activations