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

    Neuronpedia

    INDEX
    Explanations

    informal quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotes or dialogue from individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foreseeable
    -0.86
     sided
    -0.77
     correl
    -0.76
     accomp
    -0.76
     populated
    -0.75
     frontline
    -0.75
     glac
    -0.75
     contrasts
    -0.75
     encounters
    -0.74
     stem
    -0.74
    POSITIVE LOGITS
    Hey
    1.87
    Oh
    1.76
    Look
    1.68
    Yeah
    1.67
    hey
    1.66
    Well
    1.64
    You
    1.64
    Okay
    1.60
    Yo
    1.58
    Listen
    1.58
    Act Density 0.075%

    No Known Activations