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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or quantities in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vented
    -0.15
    ...↵
    -0.14
    aña
    -0.14
    ptest
    -0.14
     Miracle
    -0.14
    perl
    -0.13
    ipur
    -0.13
    curring
    -0.13
     Adam
    -0.13
     Per
    -0.13
    POSITIVE LOGITS
    000
    0.26
    Û°Û°Û°
    0.21
    600
    0.17
    ;element
    0.16
    500
    0.16
    ousand
    0.16
    ylan
    0.15
    _TRI
    0.15
    ToSelector
    0.15
    -FIRST
    0.14
    Act Density 0.076%

    No Known Activations