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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of month and year

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or significant pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manif
    -0.80
     administr
    -0.77
     arrang
    -0.69
     Vaugh
    -0.68
     destro
    -0.66
    orno
    -0.66
     helicop
    -0.66
     challeng
    -0.65
     misunder
    -0.65
     withd
    -0.64
    POSITIVE LOGITS
     SHARES
    0.91
     ][
    0.85
     Expand
    0.79
     ·
    0.77
     ILCS
    0.77
    RF
    0.71
     Minutes
    0.69
     HOU
    0.69
     Detected
    0.67
    89
    0.66
    Act Density 0.077%

    No Known Activations