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

    Neuronpedia

    INDEX
    Explanations

    mentions of a person emphasizing their involvement or presence in a situation or action

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly using the word "himself" or "themselves."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olid
    -0.84
    okin
    -0.82
    ulton
    -0.72
    CLOSE
    -0.70
     Conversation
    -0.69
    allas
    -0.67
    onal
    -0.67
     Syndicate
    -0.65
    addons
    -0.65
    mer
    -0.64
    POSITIVE LOGITS
     profess
    0.78
     acknowledged
    0.75
     predec
    0.75
     contained
    0.74
     admits
    0.73
     contradicted
    0.72
     conceded
    0.72
     admitted
    0.72
     doct
    0.72
     congratulated
    0.71
    Act Density 0.028%

    No Known Activations