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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns indicating self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kud
    -0.14
    Æ¡m
    -0.14
    .annot
    -0.13
    mant
    -0.13
     presum
    -0.13
    pres
    -0.13
     htonl
    -0.13
    اÙħÙĦ
    -0.13
    ilight
    -0.13
    grant
    -0.13
    POSITIVE LOGITS
     suppose
    0.20
     guess
    0.18
     enjoying
    0.16
     approach
    0.16
     grav
    0.15
     specialised
    0.15
    annis
    0.15
     maj
    0.15
     experiment
    0.15
     firm
    0.15
    Act Density 0.207%

    No Known Activations