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

    Neuronpedia

    INDEX
    Explanations

    the presence of personal pronouns indicating self-reference in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forChild
    -0.52
     prostu
    -0.50
     pinulongan
    -0.50
     للمعارف
    -0.47
    uose
    -0.46
    máscara
    -0.46
     Yourself
    -0.46
     itſelf
    -0.46
    니까
    -0.46
    יוחד
    -0.46
    POSITIVE LOGITS
     hadn
    1.01
     ever
    0.94
     weren
    0.93
     anything
    0.91
    anything
    0.86
     Anything
    0.74
    Anything
    0.72
     ANYTHING
    0.70
    weren
    0.68
     EVER
    0.68
    Act Density 0.122%

    No Known Activations