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

    Neuronpedia

    INDEX
    Explanations

    terms related to misunderstanding or misrepresentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trap
    -0.18
    on
    -0.17
    tant
    -0.16
    ickey
    -0.16
    tron
    -0.16
    c
    -0.15
    mw
    -0.15
    t
    -0.15
    ing
    -0.15
    trad
    -0.15
    POSITIVE LOGITS
    chie
    0.27
     mis
    0.24
    emean
    0.23
    fits
    0.22
    appropri
    0.21
    fortune
    0.21
    ellaneous
    0.20
    direct
    0.20
    ubishi
    0.20
     Mis
    0.19
    Act Density 0.008%

    No Known Activations