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

    Neuronpedia

    INDEX
    Explanations

    instances of truth and credibility assessments in claims or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑıÑĩ
    -0.15
    _activation
    -0.15
    ertz
    -0.15
     Dipl
    -0.14
     Scalars
    -0.14
    TERN
    -0.14
     Ñĥмов
    -0.14
    ãĤ¹ãĤ«
    -0.14
    eki
    -0.14
    lect
    -0.14
    POSITIVE LOGITS
    vak
    0.16
    atoi
    0.16
     categor
    0.15
    licer
    0.15
    accuracy
    0.15
     Pants
    0.14
    icity
    0.14
    ãĥ¼ãĥ«ãĥī
    0.14
    scatter
    0.14
    astic
    0.14
    Act Density 0.241%

    No Known Activations