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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the action of utilizing something for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "use" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llah
    -0.77
     Ascend
    -0.73
     Hai
    -0.68
    brother
    -0.67
    reader
    -0.66
    ellow
    -0.65
     defic
    -0.63
     4090
    -0.62
    stal
    -0.61
    antle
    -0.61
    POSITIVE LOGITS
    fully
    1.03
     condoms
    0.87
    ãĤ¢ãĥ«
    0.86
    FUL
    0.84
     phrases
    0.81
     sparing
    0.80
     leverage
    0.80
    fulness
    0.78
    illin
    0.77
    ãĥ¼ãĥĨãĤ£
    0.72
    Act Density 0.113%

    No Known Activations