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

    Neuronpedia

    INDEX
    Explanations

    phrases related to following rules or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "according to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.80
    adows
    -0.73
    estern
    -0.72
    apo
    -0.66
    anz
    -0.65
    IFT
    -0.64
    tein
    -0.64
    eg
    -0.64
    apes
    -0.64
    por
    -0.63
    POSITIVE LOGITS
    Ĥİ
    0.76
    format
    0.75
    edIn
    0.71
    eous
    0.70
    chwitz
    0.70
    Rank
    0.67
    graded
    0.66
    tains
    0.63
    iances
    0.63
    Style
    0.63
    Act Density 0.043%

    No Known Activations