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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessive adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -2.15
     Roskov
    -2.00
     itſelf
    -1.94
     Efq
    -1.91
     betweenstory
    -1.83
     Majefty
    -1.82
     Италијани
    -1.80
     pleaſure
    -1.77
     raiſ
    -1.76
     Monfieur
    -1.72
    POSITIVE LOGITS
    ↵
    1.44
     
    1.26
    .
    1.23
    ↵↵
    1.11
    '
    1.07
    ’
    1.06
    1
    1.06
     I
    1.05
    3
    1.04
    2
    1.01
    Act Density 0.422%

    No Known Activations