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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or frustration regarding societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.74
    ↵
    -0.72
    ↵↵
    -0.71
    ↵↵↵
    -0.57
    ↵↵↵↵↵
    -0.54
    <eos>
    -0.53
    ↵↵↵↵↵↵↵
    -0.49
    tagHelper
    -0.48
    ereich
    -0.47
    protoimpl
    -0.47
    POSITIVE LOGITS
     rempliss
    0.69
    labus
    0.64
    endpush
    0.64
    Viited
    0.63
    queryInterface
    0.63
    DoubleQuotes
    0.60
     Répondre
    0.59
    ipot
    0.59
    ngdoc
    0.57
    ########.
    0.57
    Act Density 0.170%

    No Known Activations