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

    Neuronpedia

    INDEX
    Explanations

    references to time and progress-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reh
    -0.17
     dut
    -0.15
     toy
    -0.15
    asty
    -0.14
     surveillance
    -0.14
     emergency
    -0.14
     Farrell
    -0.14
    é¡¿
    -0.14
     bin
    -0.14
     ض
    -0.14
    POSITIVE LOGITS
     patience
    0.18
     paci
    0.17
     wait
    0.17
    stanov
    0.17
     delay
    0.16
    speed
    0.16
    slow
    0.16
    ousse
    0.16
    _delay
    0.15
    Slow
    0.15
    Act Density 0.242%

    No Known Activations