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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference beginnings or starts of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensch
    -0.17
    HEMA
    -0.15
    bane
    -0.15
    obel
    -0.15
    [:]
    -0.14
    .copyWith
    -0.14
    pillar
    -0.14
    opo
    -0.14
    #
    -0.13
    apo
    -0.13
    POSITIVE LOGITS
    ÙĦس
    0.17
    ëŀ
    0.16
    TM
    0.15
    498
    0.14
    orf
    0.14
    iciel
    0.14
    261
    0.14
    869
    0.14
    903
    0.14
    661
    0.14
    Act Density 0.022%

    No Known Activations