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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Fresh"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fresh" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rael
    -0.61
    oried
    -0.61
    istine
    -0.60
    avery
    -0.59
    Goal
    -0.59
     Loren
    -0.58
    err
    -0.58
    ĺħ
    -0.57
    ylum
    -0.57
     Booth
    -0.57
    POSITIVE LOGITS
    ness
    1.23
    faced
    0.94
    lings
    0.93
    water
    0.90
    waters
    0.89
    lins
    0.87
    lish
    0.84
    meat
    0.83
    liness
    0.83
    forward
    0.77
    Act Density 0.038%

    No Known Activations