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

    Neuronpedia

    INDEX
    Explanations

    currency symbols and numerical ranges

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uster
    -0.69
     276
    -0.68
     376
    -0.64
     378
    -0.63
    476
    -0.62
     hurry
    -0.61
     Kers
    -0.60
     Clever
    -0.60
     McKenna
    -0.59
     disguised
    -0.58
    POSITIVE LOGITS
    9
    1.07
     9
    1.01
    949
    0.94
    909
    0.91
    930
    0.86
    10
    0.84
    90
    0.83
    911
    0.82
    910
    0.81
     920
    0.81
    Act Density 0.084%

    No Known Activations