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

    Neuronpedia

    INDEX
    Explanations

    punctuation indicating pauses or breaks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISCO
    -0.15
     gif
    -0.15
    ä»ģ
    -0.14
    urga
    -0.14
    563
    -0.14
    eri
    -0.14
    adiens
    -0.13
    isco
    -0.13
     Consolid
    -0.13
    æķı
    -0.13
    POSITIVE LOGITS
    klad
    0.17
    gang
    0.17
    adeon
    0.15
    adero
    0.14
    UTTON
    0.14
     LPARAM
    0.14
    ocale
    0.13
    ectl
    0.13
    MLElement
    0.13
    ¤ij
    0.13
    Act Density 0.000%

    No Known Activations