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

    Neuronpedia

    INDEX
    Explanations

    specific quantities or changes in measurement or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lix
    -0.15
    aight
    -0.14
    ubu
    -0.14
    enery
    -0.14
    ermal
    -0.14
    oop
    -0.14
    astle
    -0.14
    rones
    -0.14
    romise
    -0.13
    ccione
    -0.13
    POSITIVE LOGITS
    gear
    0.17
    iker
    0.16
    avs
    0.15
    èĥŀ
    0.15
    601
    0.15
    .struts
    0.14
    iad
    0.14
    ologické
    0.14
    essen
    0.14
    arat
    0.14
    Act Density 0.010%

    No Known Activations