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

    Neuronpedia

    INDEX
    Explanations

    terms related to frequency and its measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hilt
    -0.75
     uParam
    -0.72
     holand
    -0.67
    ideae
    -0.67
     conquête
    -0.66
    Дер
    -0.66
     dalamnya
    -0.66
    imgs
    -0.64
     hjemme
    -0.63
     jugé
    -0.62
    POSITIVE LOGITS
     frequencies
    1.48
     frequency
    1.43
    frequency
    1.37
     Frequ
    1.35
    frequ
    1.31
     Frequency
    1.31
     freq
    1.30
     frequ
    1.28
    Frequency
    1.28
    FREQUENCY
    1.26
    Act Density 0.117%

    No Known Activations