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

    Neuronpedia

    INDEX
    Explanations

    references to moments of decision-making and unexpected changes in plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odos
    -0.15
    isman
    -0.15
    _LP
    -0.14
     örnek
    -0.13
    foon
    -0.13
    ingleton
    -0.13
    leton
    -0.13
    uels
    -0.13
    ugas
    -0.13
     Ages
    -0.13
    POSITIVE LOGITS
     ele
    0.40
     late
    0.35
     last
    0.33
    -last
    0.28
    ele
    0.28
    late
    0.28
     Late
    0.26
     at
    0.26
     Ele
    0.25
    Late
    0.25
    Act Density 0.052%

    No Known Activations