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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs or verb phrases

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of intent or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atile
    -0.68
    naires
    -0.68
    iquette
    -0.63
    Mech
    -0.60
    keepers
    -0.60
    Delivery
    -0.60
    church
    -0.59
    feeding
    -0.59
    Bott
    -0.58
    Intern
    -0.57
    POSITIVE LOGITS
    'm
    1.16
     think
    1.01
     suppose
    1.01
     disagree
    0.98
     reiterate
    0.98
    'd
    0.95
     agree
    0.95
     want
    0.94
    'll
    0.94
     propose
    0.93
    Act Density 0.158%

    No Known Activations