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

    Neuronpedia

    INDEX
    Explanations

    programming-related technical terms and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     College
    -0.16
    วà¸ĩ
    -0.15
    anse
    -0.15
    ensely
    -0.14
    arnings
    -0.14
    hu
    -0.14
    984
    -0.14
    rimon
    -0.14
     college
    -0.14
    iesen
    -0.14
    POSITIVE LOGITS
    chal
    0.16
    outh
    0.15
    iced
    0.14
    _HEL
    0.14
    tridge
    0.14
     SPEED
    0.14
    _tac
    0.13
    niž
    0.13
    strup
    0.13
    ิà¸ģา
    0.13
    Act Density 0.001%

    No Known Activations