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

    Neuronpedia

    INDEX
    Explanations

    strings related to internet URLs

    oai_token-act-pair · gpt-3.5-turbo

    specific identifiers and components related to technology or computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pione
    -0.82
     eleph
    -0.76
     oun
    -0.70
     earthqu
    -0.68
    Ĕ
    -0.65
    aditional
    -0.65
    č
    -0.65
    ù
    -0.64
    footed
    -0.64
    ÷
    -0.64
    POSITIVE LOGITS
    /
    2.22
    /)
    1.85
    /,
    1.75
    /_
    1.70
    /-
    1.67
    /
    1.65
    /"
    1.64
    /?
    1.63
    /.
    1.60
    /(
    1.60
    Act Density 0.121%

    No Known Activations