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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to specific formulas or guidelines within a mathematical or analytical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prepositions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     we
    -0.32
     then
    -0.32
     are
    -0.30
    OR
    -0.29
    From
    -0.29
    I
    -0.28
     bå
    -0.28
    none
    -0.28
     I
    -0.28
    or
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.98
    󠁣
    0.94
    parsedMessage
    0.91
     незавершена
    0.90
    <unused17>
    0.88
    [@BOS@]
    0.88
    <unused23>
    0.88
    <unused79>
    0.88
    <unused41>
    0.88
    <pad>
    0.88
    Act Density 0.142%

    No Known Activations