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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving or resolving something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to resolving or working through situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cious
    -0.73
    interstitial
    -0.70
    âĵĺ
    -0.66
    erva
    -0.65
    avorite
    -0.64
    avin
    -0.64
    asus
    -0.63
     Pry
    -0.63
     tyr
    -0.61
    uggish
    -0.60
    POSITIVE LOGITS
    fitting
    0.87
    fitted
    0.78
    flows
    0.71
    posts
    0.71
     beforehand
    0.70
    stretched
    0.70
     how
    0.69
    flow
    0.66
    icago
    0.64
     ways
    0.64
    Act Density 0.015%

    No Known Activations