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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs expressing personal actions and feelings

    oai_token-act-pair · gpt-3.5-turbo

    references to personal connections and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     completion
    -0.80
     Comprehensive
    -0.74
     unexplained
    -0.67
     guiActiveUnfocused
    -0.67
    Ñı
    -0.66
     fundament
    -0.65
     reperto
    -0.65
     Systems
    -0.63
    Scope
    -0.63
     Fiesta
    -0.62
    POSITIVE LOGITS
     befriend
    1.10
     admire
    0.95
     marry
    0.87
     sidx
    0.86
     idol
    0.85
     )]
    0.83
     trust
    0.82
    assador
    0.82
     adore
    0.82
     trusts
    0.82
    Act Density 0.382%

    No Known Activations