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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific research and technical advancements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to clinical results and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "!
    -0.54
    Rated
    -0.53
     '.
    -0.52
    .''.
    -0.51
    .�
    -0.48
    ".
    -0.48
     ".
    -0.47
    '.
    -0.47
    cause
    -0.47
    .}
    -0.46
    POSITIVE LOGITS
    ?,
    0.75
     (),
    0.74
    *,
    0.71
    ,[
    0.67
    %,
    0.66
    !,
    0.63
    +,
    0.63
    ®,
    0.61
    ,
    0.59
     ,
    0.58
    Act Density 2.258%

    No Known Activations