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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "I" and its variations, indicating a focus on self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.86
     Theſe
    -0.84
    ſelves
    -0.79
     Houſe
    -0.78
    openConnection
    -0.77
    SEGUIR
    -0.74
    tanleria
    -0.73
    ">:
    -0.73
     Efq
    -0.73
     themſelves
    -0.72
    POSITIVE LOGITS
     am
    1.37
     Im
    1.07
    Im
    1.01
     Am
    1.00
    m
    0.93
    Am
    0.93
     im
    0.92
    am
    0.90
    Iam
    0.89
     I
    0.88
    Act Density 0.051%

    No Known Activations