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

    Neuronpedia

    INDEX
    Explanations

    HTML header tags indicating document structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     if
    -0.47
     for
    -0.46
    DockStyle
    -0.46
     et
    -0.45
     although
    -0.43
     as
    -0.43
     pool
    -0.42
     again
    -0.42
     to
    -0.41
     exit
    -0.41
    POSITIVE LOGITS
    </h2>
    0.79
    What
    0.76
    “
    0.73
    How
    0.73
    <b>
    0.73
    ing
    0.71
    Related
    0.70
    <strong>
    0.70
    Why
    0.69
    Who
    0.69
    Act Density 0.057%

    No Known Activations