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

    Neuronpedia

    INDEX
    Explanations

    future intentions or predictions expressed in a conversational tone

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

    Contractions with "'ll," "'t," or "will"

    np_acts-logits-general · gemini-2.0-flash

    you will find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.59
     geldig
    -0.56
    angana
    -0.55
     Ceramby
    -0.53
    happened
    -0.52
    parsedMessage
    -0.52
     Signalez
    -0.52
     חיצוניים
    -0.52
     tartalomajánló
    -0.51
    uxley
    -0.50
    POSITIVE LOGITS
     notice
    0.93
     want
    0.87
     regret
    0.77
     find
    0.73
     noticing
    0.68
    notice
    0.68
     notices
    0.68
    want
    0.68
     noticed
    0.67
     yourself
    0.67
    Act Density 0.110%

    No Known Activations