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

    Neuronpedia

    INDEX
    Explanations

    the word "all" at various positions within the text

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perm
    -0.68
    anova
    -0.67
    ate
    -0.67
    edin
    -0.64
    cake
    -0.61
    apa
    -0.60
    fman
    -0.59
    isol
    -0.58
    rogens
    -0.57
    illy
    -0.56
    POSITIVE LOGITS
     sorts
    0.96
     purposes
    0.91
     sake
    0.88
     kinds
    0.86
    ocating
    0.82
     eternity
    0.81
     ages
    0.81
     genders
    0.78
    igators
    0.77
    iance
    0.77
    Act Density 0.053%

    No Known Activations