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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical specifications or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡ov
    -0.16
    bung
    -0.14
    lh
    -0.14
    è¯Ĭ
    -0.14
    odon
    -0.13
     Undefined
    -0.13
    bris
    -0.13
    agers
    -0.13
    Å¡en
    -0.13
    *num
    -0.13
    POSITIVE LOGITS
    ala
    0.15
    orraine
    0.15
    iction
    0.15
    ropolis
    0.15
     Bail
    0.14
    iento
    0.14
    toa
    0.14
    ze
    0.14
    ibus
    0.14
     Nations
    0.13
    Act Density 0.044%

    No Known Activations