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

    Neuronpedia

    INDEX
    Explanations

    terms related to data security and technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kish
    -0.15
    ĥ
    -0.15
     лиÑĪ
    -0.14
     Poz
    -0.13
    ỡ
    -0.13
     sake
    -0.13
    onus
    -0.13
    287
    -0.13
    _boost
    -0.13
    /docs
    -0.13
    POSITIVE LOGITS
    instead
    0.28
     instead
    0.28
     Äijá»ĥ
    0.27
     to
    0.25
     ÑĩÑĤобÑĭ
    0.24
     вмеÑģÑĤ
    0.23
    à¹ĥà¸Ļà¸ģาร
    0.23
     Ñīоб
    0.19
    æĿ¥
    0.19
     Instead
    0.18
    Act Density 0.229%

    No Known Activations