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

    Neuronpedia

    INDEX
    Explanations

    references related to fandom or audience engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chg
    -0.18
    aira
    -0.15
    acob
    -0.15
    ault
    -0.15
    tier
    -0.15
     Chill
    -0.15
    iman
    -0.14
    imest
    -0.14
    stå
    -0.14
     chim
    -0.14
    POSITIVE LOGITS
     anything
    0.21
    anything
    0.19
    ëĮĢë¡ľ
    0.19
    anlı
    0.17
     Anything
    0.17
     correctly
    0.17
    Äĥn
    0.15
    .gs
    0.15
    oct
    0.14
    polation
    0.14
    Act Density 0.036%

    No Known Activations