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

    Neuronpedia

    INDEX
    Explanations

    mention of URLs and possibly formatting symbols

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or expressions of emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.91
    ensibly
    -0.76
    abwe
    -0.73
     centrally
    -0.69
     estranged
    -0.69
    ulkan
    -0.66
    avorite
    -0.65
     antit
    -0.65
    olicy
    -0.65
    ocating
    -0.64
    POSITIVE LOGITS
    Anyway
    1.06
    ³³³³³³³³³³³³³³³³
    1.00
    ³³³³
    0.95
    ³³³³³³³³
    0.95
     Anyway
    0.95
    âĶĢâĶĢâĶĢâĶĢ
    0.91
    ³³³
    0.87
    rawdownloadcloneembedreportprint
    0.83
    âĹ¼
    0.82
    ³³
    0.80
    Act Density 0.374%

    No Known Activations