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

    Neuronpedia

    INDEX
    Explanations

    affirmative expressions of confidence or certainty

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

    expressions of agreement or affirmation

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

    sure followed by pronoun, article, or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.78
    audiovisuel
    -0.75
    Portály
    -0.68
    PreferredItem
    -0.67
    medriver
    -0.66
     ExecuteAsync
    -0.66
    utivo
    -0.66
    \}\\
    -0.65
    haway
    -0.65
    IUrlHelper
    -0.65
    POSITIVE LOGITS
     thing
    0.84
     enough
    0.69
    fire
    0.66
     wish
    0.66
     THING
    0.64
     hope
    0.64
     beats
    0.58
    nuff
    0.58
    enough
    0.57
     saja
    0.56
    Act Density 0.008%

    No Known Activations