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

    Neuronpedia

    INDEX
    Explanations

    references to anonymity and the act of speaking about sensitive issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IALIZED
    -0.17
    _ENDIAN
    -0.16
    наÑĢ
    -0.16
    rani
    -0.15
    ritch
    -0.15
     subscript
    -0.15
    ãĤ¼
    -0.14
     Wor
    -0.14
    най
    -0.14
    irc
    -0.14
    POSITIVE LOGITS
     anonymity
    0.32
     condition
    0.29
    anonymous
    0.26
     anonymous
    0.25
     anonym
    0.25
     anonymously
    0.25
     Anonymous
    0.25
     speaking
    0.24
     anon
    0.23
     Condition
    0.23
    Act Density 0.014%

    No Known Activations