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

    Neuronpedia

    INDEX
    Explanations

    references to comments and commentary within articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rok
    -0.16
    emouth
    -0.16
    ãĥĩãĥ«
    -0.15
    à¥ĩत
    -0.15
    upos
    -0.14
    combe
    -0.14
    _constant
    -0.14
    ning
    -0.14
    aln
    -0.14
    ãĥ³ãĥĶ
    -0.14
    POSITIVE LOGITS
    aries
    0.28
    aires
    0.22
    ary
    0.20
    ghan
    0.19
    eting
    0.19
    ators
    0.18
    ypes
    0.17
    ers
    0.17
    ariat
    0.17
    atory
    0.17
    Act Density 0.035%

    No Known Activations