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

    Neuronpedia

    INDEX
    Explanations

    references to formal logical systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensual
    -0.15
    icus
    -0.14
    åĨµ
    -0.14
    RTOS
    -0.14
     Redemption
    -0.13
    -prepend
    -0.13
    æĻ¨
    -0.13
    .Scheme
    -0.13
     Eisen
    -0.13
    wn
    -0.13
    POSITIVE LOGITS
     modal
    0.25
    Modal
    0.23
     Modal
    0.22
    modal
    0.21
     Lewis
    0.21
     counter
    0.20
    _modal
    0.20
    Lewis
    0.18
    -modal
    0.18
     mod
    0.18
    Act Density 0.009%

    No Known Activations