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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly periods and dashes, along with shifts in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eum
    -0.15
    веÑģÑĤи
    -0.15
    edException
    -0.15
     onDataChange
    -0.15
    seau
    -0.15
    é¦Ļ
    -0.15
    akin
    -0.14
    à¥
    -0.14
    _strerror
    -0.14
     вÑģÑĤÑĥп
    -0.14
    POSITIVE LOGITS
    eco
    0.17
     Newman
    0.16
     d
    0.15
    apur
    0.15
    229
    0.14
     forks
    0.14
    away
    0.14
    VML
    0.14
    atte
    0.14
     Neh
    0.14
    Act Density 0.062%

    No Known Activations