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

    Neuronpedia

    INDEX
    Explanations

    sections or indicators of structure in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itzer
    -0.16
    erm
    -0.15
     neutral
    -0.15
     rem
    -0.15
    amo
    -0.15
     ones
    -0.14
     ruling
    -0.14
     fully
    -0.14
    aly
    -0.14
    526
    -0.14
    POSITIVE LOGITS
    å´İ
    0.16
    iland
    0.15
    dragon
    0.14
    toupper
    0.14
    agus
    0.14
    inerary
    0.14
    гал
    0.14
    umbs
    0.14
    ToOne
    0.14
    _ASSUME
    0.14
    Act Density 0.018%

    No Known Activations