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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the pronoun "I" across various contexts

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

    Statements of personal opinion after "I"

    np_acts-logits-general · gemini-2.0-flash

    "I" statements expressing personal beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.61
    RegressionTest
    -0.60
     Besoin
    -0.56
    colgroup
    -0.55
    cieux
    -0.54
    ës
    -0.54
     rhestr
    -0.52
    الإنجليزية
    -0.52
    usercontent
    -0.51
     kasarigan
    -0.50
    POSITIVE LOGITS
     personally
    0.75
     happen
    0.63
     myself
    0.63
     guarantee
    0.62
     agree
    0.61
     bet
    0.59
    happens
    0.57
    agree
    0.57
    happen
    0.57
     himself
    0.56
    Act Density 0.239%

    No Known Activations