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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word 'blend'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blend" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.78
    resy
    -0.75
     reper
    -0.67
    phis
    -0.66
    pter
    -0.65
    mond
    -0.64
    ensional
    -0.62
    nai
    -0.62
     Asked
    -0.60
    irez
    -0.59
    POSITIVE LOGITS
     blend
    0.93
     blends
    0.91
     blending
    0.88
     seamlessly
    0.79
    coe
    0.74
    endor
    0.72
     Flavoring
    0.71
    wana
    0.70
    waters
    0.70
    ibilities
    0.67
    Act Density 0.012%

    No Known Activations