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

    Neuronpedia

    INDEX
    Explanations

    phrases related to function definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $core
    -0.16
    виÑĩ
    -0.15
    bite
    -0.15
    کت
    -0.15
    anson
    -0.15
    _marshall
    -0.14
    çħ
    -0.14
    anders
    -0.14
    unger
    -0.14
    otland
    -0.14
    POSITIVE LOGITS
    per
    0.18
    eggies
    0.15
    arget
    0.15
    ấy
    0.15
    urt
    0.14
    noop
    0.14
    orgen
    0.13
     boom
    0.13
    ylene
    0.13
    ello
    0.13
    Act Density 0.070%

    No Known Activations