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

    Neuronpedia

    INDEX
    Explanations

    terms related to interruptive processes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mund
    -0.17
    AndWait
    -0.16
    essler
    -0.15
    acic
    -0.15
    icie
    -0.15
    iaux
    -0.14
    .Align
    -0.14
    üb
    -0.14
    fld
    -0.14
    à¹Īà¸Ń
    -0.14
    POSITIVE LOGITS
    LIKELY
    0.15
    omatic
    0.15
     max
    0.14
    ossa
    0.14
    ém
    0.14
    jab
    0.14
    usk
    0.13
    max
    0.13
    594
    0.13
    oses
    0.13
    Act Density 0.008%

    No Known Activations