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

    Neuronpedia

    INDEX
    Explanations

    reflections on self-identity and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MessageBoxIcon
    -0.79
    er
    -0.79
     Pitman
    -0.78
     Bue
    -0.74
     Tiz
    -0.73
    ้น
    -0.73
     Piz
    -0.71
     Garrick
    -0.71
    hat
    -0.69
    ֵי
    -0.68
    POSITIVE LOGITS
     herself
    1.83
     yourself
    1.73
    herself
    1.72
     Himself
    1.72
     Yourself
    1.72
     himself
    1.72
    myself
    1.71
     myself
    1.71
    Yourself
    1.68
    himself
    1.64
    Act Density 0.100%

    No Known Activations