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

    Neuronpedia

    INDEX
    Explanations

    mention of time phrases

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cause
    -0.65
    ãĥ¥
    -0.65
    Override
    -0.64
    grain
    -0.64
    Deal
    -0.63
     intermediary
    -0.62
    Attach
    -0.61
    Your
    -0.60
    Optional
    -0.60
    opl
    -0.59
    POSITIVE LOGITS
     however
    0.97
     meanwhile
    0.82
     citing
    0.75
     according
    0.73
     although
    0.71
     Shank
    0.71
     huh
    0.71
     though
    0.71
     Kinnikuman
    0.68
     Vie
    0.67
    Act Density 0.640%

    No Known Activations