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

    Neuronpedia

    INDEX
    Explanations

    terms related to a physical action of bringing something down

    oai_token-act-pair · gpt-3.5-turbo

    terms related to food preparation and cooking measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pak
    -0.76
    ois
    -0.72
    Daddy
    -0.69
    Tur
    -0.67
    ifiable
    -0.66
    bit
    -0.66
    actively
    -0.65
    opath
    -0.64
    fork
    -0.64
    NUM
    -0.63
    POSITIVE LOGITS
    etheless
    1.01
     downed
    0.89
    ĪĴ
    0.88
    »Ĵ
    0.86
    ĸļ
    0.84
    isance
    0.79
    ĨĴ
    0.73
    pread
    0.73
    ĺħ
    0.72
    ience
    0.72
    Act Density 0.029%

    No Known Activations