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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-identity and introspection

    oai_token-act-pair · gpt-3.5-turbo

    references to self-identity and personal definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ratification
    -0.81
     confisc
    -0.79
     impeachment
    -0.71
     moratorium
    -0.69
     confiscated
    -0.68
     shotguns
    -0.68
     restart
    -0.67
     irrigation
    -0.67
     ringing
    -0.67
     inspections
    -0.65
    POSITIVE LOGITS
     selves
    1.12
     individuality
    1.01
     persona
    1.00
    selves
    0.90
    lik
    0.87
     personality
    0.86
    apeshifter
    0.84
     oneself
    0.84
    eness
    0.84
    Person
    0.83
    Act Density 0.421%

    No Known Activations