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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to oneself or others, and verbs indicating a change or current state of being

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements about identity and self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arya
    -0.74
     breeze
    -0.68
    artifacts
    -0.66
     margin
    -0.61
     clearance
    -0.60
     hazard
    -0.60
     Checking
    -0.59
     Clever
    -0.56
    elsius
    -0.56
    ragon
    -0.55
    POSITIVE LOGITS
    Reloaded
    0.70
     profess
    0.68
    uably
    0.68
     pretended
    0.64
    rir
    0.64
    rencies
    0.63
    Self
    0.62
    uer
    0.61
     portrays
    0.60
     Become
    0.59
    Act Density 0.115%

    No Known Activations