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

    Neuronpedia

    INDEX
    Explanations

    words related to classification and categorization of entities or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALA
    -0.17
    ละ
    -0.16
    ucken
    -0.15
    ngth
    -0.15
    otes
    -0.15
    θι
    -0.15
    Ñİк
    -0.14
    ffield
    -0.14
    pires
    -0.14
    {{{
    -0.14
    POSITIVE LOGITS
     Dup
    0.15
    [__
    0.15
    erne
    0.15
    isans
    0.14
    é¼ĵ
    0.14
    ÑĤеÑĢн
    0.14
    ichi
    0.13
    leta
    0.13
     Guard
    0.13
     Camp
    0.13
    Act Density 0.436%

    No Known Activations