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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to the concept of functioning or operation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "function"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jen
    -0.68
     Hemp
    -0.67
    cott
    -0.67
    æĢ
    -0.66
    corn
    -0.65
     millenn
    -0.64
     Upton
    -0.62
     Crus
    -0.60
    cot
    -0.59
    lake
    -0.58
    POSITIVE LOGITS
     functions
    0.84
    ioned
    0.84
    xes
    0.83
    alities
    0.82
    ality
    0.81
    ional
    0.80
     function
    0.78
    abilities
    0.76
    ivity
    0.75
    iona
    0.75
    Act Density 0.012%

    No Known Activations