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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of month and day

    oai_token-act-pair · gpt-3.5-turbo

    dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.73
     mathemat
    -0.68
    ortunately
    -0.67
     unnecess
    -0.67
     exha
    -0.67
     arrang
    -0.62
     councill
    -0.61
     behavi
    -0.61
     predec
    -0.60
    aditional
    -0.59
    POSITIVE LOGITS
     27
    1.04
     29
    1.04
     26
    1.03
     23
    1.02
     24
    1.01
     28
    1.01
     19
    1.00
     13
    1.00
     31
    0.98
     22
    0.98
    Act Density 0.048%

    No Known Activations