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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and references to self

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.18
     massaggi
    -0.15
    ÏĦÏİν
    -0.15
    ÑĢÑĸм
    -0.15
    /or
    -0.15
    oodles
    -0.15
    ignon
    -0.14
    olia
    -0.14
    igation
    -0.14
    .onDestroy
    -0.14
    POSITIVE LOGITS
     else
    0.18
     simply
    0.18
     another
    0.17
     equival
    0.16
    phans
    0.16
     just
    0.15
    ner
    0.15
    ignal
    0.15
     s
    0.14
     any
    0.14
    Act Density 0.120%

    No Known Activations