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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating examples or specifications

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

    "as" (or similar words) followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    introducing lists of examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     XNUMX
    -0.62
    ValueStyle
    -0.60
    Carriera
    -0.59
    UnusedPrivate
    -0.57
     båda
    -0.56
     ſame
    -0.55
    contentPane
    -0.54
     незавершена
    -0.54
     насељу
    -0.53
    ContentAsync
    -0.53
    POSITIVE LOGITS
     those
    1.52
    those
    1.25
    :
    1.10
     Those
    1.04
     ones
    0.99
     namely
    0.98
    Those
    0.98
    namely
    0.96
     celles
    0.93
     THOSE
    0.88
    Act Density 0.445%

    No Known Activations