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

    Neuronpedia

    INDEX
    Explanations

    numerical values and accompanying contextual words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.08
    istrovstvÃŃ
    -0.08
    renom
    -0.08
    ewan
    -0.07
    raya
    -0.07
    seau
    -0.07
    izik
    -0.07
     Geile
    -0.07
    .gdx
    -0.07
     factorial
    -0.07
    POSITIVE LOGITS
     value
    0.08
    value
    0.07
     Townsend
    0.07
    ê°Ĵ
    0.06
     giá
    0.06
     nghá»ĭ
    0.06
    mark
    0.06
     tune
    0.06
     LOD
    0.06
     values
    0.06
    Act Density 0.001%

    No Known Activations