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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and phrases indicating personal experiences or emotions

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

    "I" followed by verbs expressing opinion/desire

    np_acts-logits-general · gemini-2.0-flash

    I statements about personal beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.92
    AndEndTag
    -0.71
    écnicas
    -0.66
    erview
    -0.65
     Roskov
    -0.64
    دانشنامهٔ
    -0.63
    )))));
    -0.63
     MediatR
    -0.63
    orgeous
    -0.62
    DrawerToggle
    -0.62
    POSITIVE LOGITS
     certainly
    0.74
     hope
    0.71
     wouldn
    0.70
     jedenfalls
    0.67
     gotta
    0.66
     البته
    0.65
     even
    0.63
     just
    0.63
     shouldn
    0.60
     still
    0.59
    Act Density 0.261%

    No Known Activations