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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by emotions or feelings

    oai_token-act-pair · gpt-3.5-turbo

    the use of the first-person pronoun "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INGTON
    -0.66
    ailability
    -0.63
    ipedia
    -0.63
    Saharan
    -0.62
     Billboard
    -0.62
    ãĥĬ
    -0.61
    urrencies
    -0.61
    ipation
    -0.60
    flation
    -0.60
     Gallup
    -0.59
    POSITIVE LOGITS
     presume
    1.15
     suppose
    1.06
    'm
    1.06
     believe
    0.95
     guess
    0.94
     assume
    0.94
    ñ
    0.92
     dunno
    0.90
    ggy
    0.87
     pity
    0.84
    Act Density 0.298%

    No Known Activations