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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated contextual elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _PD
    -0.18
    imeline
    -0.15
    ndon
    -0.15
    طار
    -0.15
    abad
    -0.14
     Sham
    -0.14
    kontakte
    -0.14
    pedo
    -0.14
    illos
    -0.14
    aclass
    -0.14
    POSITIVE LOGITS
    ÑĢей
    0.15
    ×Ļ
    0.14
    stice
    0.14
    CHIP
    0.14
    cons
    0.14
    egree
    0.14
    /problem
    0.14
    TRL
    0.13
    cient
    0.13
     facto
    0.13
    Act Density 0.006%

    No Known Activations