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

    Neuronpedia

    INDEX
    Explanations

    references to belief or belief systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yen
    -0.17
    sdale
    -0.17
    yy
    -0.17
    y
    -0.16
    ffe
    -0.16
    quila
    -0.15
    yh
    -0.15
    yor
    -0.15
    pg
    -0.15
    emi
    -0.14
    POSITIVE LOGITS
    gium
    0.20
    tran
    0.19
    azaar
    0.19
    iefs
    0.18
    grade
    0.17
    isle
    0.16
    amy
    0.16
    ieving
    0.16
    inda
    0.16
    atrix
    0.16
    Act Density 0.008%

    No Known Activations