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

    Neuronpedia

    INDEX
    Explanations

    dialogue and quotations in the text

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

    "said" followed by a comma or period

    np_acts-logits-general · gemini-2.0-flash

    manner of speaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.80
     transfieras
    -0.68
    Personensuche
    -0.67
     powied
    -0.66
     autorytatywna
    -0.66
    arXiv
    -0.62
    MigrationBuilder
    -0.62
     newOwner
    -0.61
    saraba
    -0.60
     faid
    -0.58
    POSITIVE LOGITS
     while
    0.86
     sambil
    0.71
     softly
    0.71
     after
    0.69
     aloud
    0.68
     whilst
    0.66
     referring
    0.65
     terwijl
    0.64
     with
    0.63
     calmly
    0.63
    Act Density 0.088%

    No Known Activations