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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong recommendation or necessity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or measurement of conditions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olded
    -0.70
     Browns
    -0.61
     Romanian
    -0.59
    aeper
    -0.59
     Rost
    -0.59
     MET
    -0.58
     ticket
    -0.58
     GPL
    -0.58
     Chemistry
    -0.57
    agra
    -0.56
    POSITIVE LOGITS
     imaginable
    0.87
    soever
    0.80
     whatsoever
    0.77
     conceivable
    0.75
    Camera
    0.73
     except
    0.71
    aws
    0.70
    udos
    0.66
    innacle
    0.66
    antage
    0.66
    Act Density 0.093%

    No Known Activations