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

    Neuronpedia

    INDEX
    Explanations

    references to statistics and comparisons regarding different groups or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to the increase in quantifiable phenomena related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lazarus
    -0.74
     Abdel
    -0.72
    CHAT
    -0.67
    cknow
    -0.67
     Whip
    -0.66
    RAW
    -0.65
    ij士
    -0.64
     Jinn
    -0.63
    eston
    -0.61
    ALSE
    -0.60
    POSITIVE LOGITS
     than
    1.54
    than
    1.23
     Than
    0.98
    erous
    0.85
    catentry
    0.80
    efficient
    0.77
     bang
    0.75
     hassle
    0.73
    worthy
    0.71
     sidx
    0.69
    Act Density 0.202%

    No Known Activations