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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIL
    -0.85
    BAT
    -0.77
    ellectual
    -0.77
    Free
    -0.74
    Network
    -0.73
     Doodle
    -0.68
    FREE
    -0.68
    ETH
    -0.67
    DA
    -0.67
    Adapt
    -0.66
    POSITIVE LOGITS
     onwards
    1.19
     thereafter
    1.08
     onward
    1.08
     then
    0.94
     culminated
    0.93
     thence
    0.93
     thus
    0.92
     consequently
    0.91
     subsequently
    0.91
     thereby
    0.86
    Act Density 0.165%

    No Known Activations