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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a shift or change in perspective or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CFG
    -0.15
    urm
    -0.14
    enet
    -0.14
    ebo
    -0.14
    xon
    -0.14
    ittle
    -0.14
    enity
    -0.14
    AGO
    -0.14
    enia
    -0.14
    elm
    -0.14
    POSITIVE LOGITS
    ÙĨØ´
    0.15
    ç¾
    0.14
     Dame
    0.14
    ordes
    0.14
    instead
    0.14
     ((__
    0.14
    emez
    0.13
    oner
    0.13
    lobal
    0.13
    Instead
    0.13
    Act Density 0.036%

    No Known Activations