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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols in the text

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

    specific following tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Harms
    -0.39
    enumi
    -0.39
    .
    -0.36
    quema
    -0.34
    Several
    -0.33
     this
    -0.33
     descendre
    -0.33
     táctil
    -0.33
    relsen
    -0.32
    리
    -0.32
    POSITIVE LOGITS
    Vidite
    0.71
    <unused28>
    0.69
    <unused52>
    0.69
    <unused23>
    0.69
    <unused41>
    0.69
    <unused16>
    0.69
    ſſung
    0.69
    <unused8>
    0.69
    <unused3>
    0.69
    [@BOS@]
    0.69
    Act Density 0.038%

    No Known Activations