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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical proofs and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.46
    begin
    -0.39
    my
    -0.37
    <
    -0.35
     
    -0.33
    enumi
    -0.33
    '
    -0.33
    ↵
    -0.32
    ’
    -0.32
    \
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.85
     surla
    0.79
    parsedMessage
    0.78
    PreferredItem
    0.77
    tvguidetime
    0.72
    <unused28>
    0.71
    <unused52>
    0.71
    <unused3>
    0.71
    <unused79>
    0.71
    [@BOS@]
    0.71
    Act Density 11.144%

    No Known Activations