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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal feelings and thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.96
     itſelf
    -0.94
     doubtnut
    -0.91
     ་་
    -0.90
     Majefty
    -0.89
    ſelf
    -0.85
    )";
    -0.85
     myſelf
    -0.84
     Anſ
    -0.81
     Jefus
    -0.78
    POSITIVE LOGITS
    mara
    0.57
     Nowadays
    0.54
     thing
    0.54
     nice
    0.53
     it
    0.51
     advices
    0.51
     everybody
    0.50
     somebody
    0.50
    !
    0.50
     ON
    0.49
    Act Density 0.882%

    No Known Activations