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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating duration or time served in various roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eck
    -0.18
    ysa
    -0.15
    otto
    -0.15
    ì´
    -0.14
    ÙĩÙĨ
    -0.14
    ocu
    -0.13
     zů
    -0.13
    istine
    -0.13
    velope
    -0.13
    isas
    -0.13
    POSITIVE LOGITS
     close
    0.33
     over
    0.31
     most
    0.30
     since
    0.27
     last
    0.26
     well
    0.24
     going
    0.24
     past
    0.23
     quite
    0.22
     many
    0.22
    Act Density 0.039%

    No Known Activations