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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¨
    -2.79
    Ĵ
    -2.63
    ¥
    -2.59
    -2.59
    ↵
    -2.59
    ↵
    -2.59
    -2.59
    ↵  ³³³
    -2.59
    č↵
    -2.59
    ↵
    -2.59
    POSITIVE LOGITS
    criptor
    2.19
    cción
    1.72
    onz
    1.70
    fee
    1.69
    onde
    1.66
    anguage
    1.56
    ppo
    1.50
    iast
    1.50
    atto
    1.50
    ecl
    1.49
    Act Density 4.617%

    No Known Activations