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

    Neuronpedia

    INDEX
    Explanations

    common phrases and conjunctions indicating sequence or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amework
    -0.14
    subclass
    -0.14
    enne
    -0.14
    .AddComponent
    -0.14
    raphics
    -0.13
    ource
    -0.13
    conto
    -0.13
    uplic
    -0.12
    лаÑĤ
    -0.12
    ses
    -0.12
    POSITIVE LOGITS
    ftware
    0.26
    bsite
    0.22
    raq
    0.21
    apons
    0.21
    IGINAL
    0.20
    adays
    0.19
    odore
    0.18
    ctrine
    0.17
    cluded
    0.17
    enticate
    0.17
    Act Density 0.064%

    No Known Activations