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

    Neuronpedia

    INDEX
    Explanations

    quantitative values mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and statistical metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Situation
    -0.73
     ART
    -0.70
    Oper
    -0.68
     Rein
    -0.68
     Sear
    -0.66
     Bellev
    -0.65
    ourge
    -0.63
     Beaver
    -0.63
    odynam
    -0.62
    clinical
    -0.61
    POSITIVE LOGITS
     rpm
    0.83
    mb
    0.80
     yuan
    0.80
     RPM
    0.77
     cents
    0.75
    taboola
    0.73
    uters
    0.73
    ¼
    0.70
     mins
    0.69
    000
    0.69
    Act Density 0.181%

    No Known Activations