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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "otherness" or external entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allon
    -0.16
    ycz
    -0.14
    acker
    -0.13
    iko
    -0.13
    amar
    -0.13
    Certificates
    -0.13
    schemas
    -0.13
     reputation
    -0.13
    ses
    -0.13
    _bw
    -0.13
    POSITIVE LOGITS
     words
    0.46
    words
    0.39
     Words
    0.33
    Words
    0.32
    .words
    0.30
    _words
    0.29
     other
    0.26
    WORDS
    0.23
    other
    0.22
    (words
    0.22
    Act Density 0.008%

    No Known Activations