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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating existence or introduction of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    It detects the beginning of a text segment (start-of-sequence / sentence or question openings).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.92
    mybatisplus
    -0.92
    :+:
    -0.87
    >--}}
    -0.86
    Referências
    -0.84
    Clik
    -0.83
    ongoose
    -0.77
    Παραπομπές
    -0.77
     utafitiHapana
    -0.77
    enumi
    -0.76
    POSITIVE LOGITS
    When
    0.46
    ↵↵
    0.45
    In
    0.43
    While
    0.42
    ↵
    0.41
    ご覧
    0.41
    After
    0.41
    bicara
    0.40
    isierung
    0.40
    My
    0.40
    Act Density 0.513%

    No Known Activations