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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Never"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aminer
    -0.16
    avaÅŁ
    -0.15
    ÙĨاÙħÙĩ
    -0.15
    ê¸°ë¡ľ
    -0.15
     jadx
    -0.15
    .builders
    -0.15
     publi
    -0.14
    erna
    -0.14
    ISMATCH
    -0.14
    Å¡t
    -0.14
    POSITIVE LOGITS
     ar
    0.15
    iche
    0.15
    entions
    0.14
    inem
    0.14
     Sah
    0.14
    okens
    0.14
    unger
    0.14
    amet
    0.14
    anke
    0.13
    otal
    0.13
    Act Density 0.010%

    No Known Activations