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

    Neuronpedia

    INDEX
    Explanations

    comparisons and evaluations regarding standards, practices, or performances across different entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opus
    -0.17
    iazza
    -0.15
    ycler
    -0.15
    abar
    -0.14
    ixo
    -0.14
    elsen
    -0.14
    cks
    -0.14
    _ALIGN
    -0.14
    asses
    -0.14
    els
    -0.14
    POSITIVE LOGITS
     between
    0.29
     two
    0.29
    both
    0.29
    between
    0.28
    two
    0.28
    _both
    0.28
     both
    0.28
     Between
    0.28
    Both
    0.27
    _two
    0.26
    Act Density 0.202%

    No Known Activations