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

    Neuronpedia

    INDEX
    Explanations

    quantitative metrics and values related to assessments, statistics, and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utures
    -0.17
     (~
    -0.15
    eka
    -0.15
    914
    -0.15
    opoulos
    -0.15
    ABCDEFGHI
    -0.15
     '..',
    -0.15
    opak
    -0.14
     (>
    -0.14
    lep
    -0.14
    POSITIVE LOGITS
     of
    0.31
    of
    0.26
    .of
    0.21
     equal
    0.18
     của
    0.18
    onna
    0.17
    	of
    0.16
    _of
    0.16
     no
    0.16
     between
    0.15
    Act Density 0.064%

    No Known Activations