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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -3.64
     Efq
    -3.63
     Theſe
    -3.56
     itſelf
    -3.51
     Majefty
    -3.34
     ―――――
    -3.32
     Reſ
    -3.31
     Jefus
    -3.29
     myſelf
    -3.27
     ſeveral
    -3.25
    POSITIVE LOGITS
     I
    3.56
     we
    2.13
     he
    2.09
     i
    1.99
    I
    1.98
     
    1.92
     A
    1.80
     We
    1.70
     He
    1.69
     (
    1.65
    Act Density 0.464%

    No Known Activations