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

    Neuronpedia

    INDEX
    Explanations

    instances of capitalized words that likely represent titles or significant terms

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

    the beginning of text documents or passages.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    TextBoxColumn
    -0.49
    <eos>
    -0.48
    HasIndex
    -0.40
    table
    -0.39
    </h1>
    -0.37
     (
    -0.37
     par
    -0.36
     mu
    -0.34
     π
    -0.34
     ins
    -0.34
    POSITIVE LOGITS
     houſe
    0.69
     kasarigan
    0.67
    DockStyle
    0.65
    niſſe
    0.65
     transfieras
    0.65
     ſche
    0.62
     fashiola
    0.62
     Houſe
    0.61
     تضيفلها
    0.61
    ﹧
    0.61
    Act Density 0.554%

    No Known Activations