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

    Neuronpedia

    INDEX
    Explanations

    phrases that address the reader directly

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

    Follows "you" and precedes verbs or auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.71
     שוליים
    -0.70
    bewerken
    -0.66
     TestBed
    -0.60
    клопе
    -0.54
     CURIAM
    -0.54
    WithIOException
    -0.53
    PYX
    -0.52
     հղումներ
    -0.52
    parsedMessage
    -0.51
    POSITIVE LOGITS
     wondering
    0.89
     wondered
    0.76
     wonder
    0.75
    Wondering
    0.69
     curious
    0.68
    wonder
    0.68
     missed
    0.64
     haven
    0.62
     Missed
    0.61
     alguna
    0.60
    Act Density 0.150%

    No Known Activations