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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional statements with 'if' and comparisons with 'as much as'

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that introduce uncertainty or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Els
    -0.80
    marine
    -0.71
    eln
    -0.65
    atron
    -0.65
    arsity
    -0.64
    peat
    -0.62
    alon
    -0.61
    oney
    -0.60
    oots
    -0.60
    Assembly
    -0.59
    POSITIVE LOGITS
     disclaim
    0.89
     disclaimer
    0.72
     Odd
    0.67
    nikov
    0.64
     myths
    0.59
    claimer
    0.59
    math
    0.59
    cknowled
    0.58
     REPORT
    0.56
     conclud
    0.56
    Act Density 0.165%

    No Known Activations