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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs indicating behavior or interaction

    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
     Squid
    -0.68
    umption
    -0.64
     Proced
    -0.62
     Boolean
    -0.61
     completion
    -0.60
     sorcery
    -0.60
     guiActiveUnfocused
    -0.59
     Volcano
    -0.59
     fundament
    -0.59
     Sorceress
    -0.58
    POSITIVE LOGITS
     adore
    0.94
     admire
    0.90
     trusts
    0.87
     trusted
    0.86
    igl
    0.83
     interviewed
    0.80
     befriend
    0.79
     affection
    0.79
     victimized
    0.79
    assies
    0.78
    Act Density 0.335%

    No Known Activations