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

    Neuronpedia

    INDEX
    Explanations

    instances of process-related terminology and expressions of uncertainty in discussions

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

    Follows "about," "think," or is a bracketed letter

    np_acts-logits-general · gemini-2.0-flash

    about it or think about it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.77
    lapsingToolbar
    -0.65
    ngrx
    -0.59
    PYX
    -0.57
    providedIn
    -0.56
     CreateTagHelper
    -0.56
     AssemblyCulture
    -0.56
    íše
    -0.55
    nodoc
    -0.54
     gespannt
    -0.53
    POSITIVE LOGITS
     it
    1.26
     things
    0.90
     thing
    0.87
    things
    0.81
    Things
    0.79
    It
    0.79
     Things
    0.74
     THINGS
    0.70
     ello
    0.69
    thing
    0.69
    Act Density 0.211%

    No Known Activations