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

    Neuronpedia

    INDEX
    Explanations

    times expressed in a specific format: hours and minutes, followed by a colon, and then a single digit number

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ificant
    -0.72
    inarily
    -0.66
    abouts
    -0.66
     authority
    -0.62
     behavi
    -0.59
    erness
    -0.58
     escort
    -0.57
     reconciliation
    -0.57
     purse
    -0.57
     resc
    -0.57
    POSITIVE LOGITS
    00
    1.18
    59
    1.17
    30
    1.11
    58
    1.08
    53
    1.04
    56
    1.03
    54
    1.03
    51
    1.02
    57
    1.02
    55
    1.02
    Act Density 0.037%

    No Known Activations