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

    Neuronpedia

    INDEX
    Explanations

    references to fractions or portions, particularly relating to "half."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èªĮ
    -0.17
    ле
    -0.17
    chyb
    -0.16
    avin
    -0.16
    IDD
    -0.16
    insky
    -0.15
    usz
    -0.15
    ils
    -0.15
    ÅĻeh
    -0.14
    emme
    -0.14
    POSITIVE LOGITS
    ths
    0.17
     dozen
    0.16
     Exec
    0.14
    rd
    0.14
    imson
    0.14
    rs
    0.14
     Nam
    0.13
    ï¸ı
    0.13
     Warn
    0.13
     times
    0.13
    Act Density 0.042%

    No Known Activations