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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate statistics or numerical values in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.40
    (
    -0.27
    's
    -0.26
    &nbsp
    -0.25
    :
    -0.25
    "
    -0.24
    're
    -0.23
    ’s
    -0.23
    <br
    -0.23
    ↵↵
    -0.22
    POSITIVE LOGITS
    /'
    0.21
    âĢ²
    0.16
    ãĢģ“
    0.15
    ï¼Į“
    0.15
    ãĢģãĢĮ
    0.15
    [$_
    0.14
    ï¸ı
    0.14
    ulses
    0.14
    egal
    0.14
    ®,
    0.14
    Act Density 1.098%

    No Known Activations