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

    Neuronpedia

    INDEX
    Explanations

    questions containing the word "if"

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abal
    -0.72
    _-
    -0.68
    lines
    -0.67
    etheless
    -0.64
    ulic
    -0.64
    alde
    -0.62
    advertising
    -0.62
    line
    -0.62
    tc
    -0.61
    iege
    -0.61
    POSITIVE LOGITS
     suspic
    0.86
    Daddy
    0.74
    amera
    0.70
    ihad
    0.68
     mosqu
    0.67
     hairc
    0.67
     passwords
    0.67
     explan
    0.66
     millenn
    0.65
     indecent
    0.64
    Act Density 0.085%

    No Known Activations