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

    Neuronpedia

    INDEX
    Explanations

    terms related to compiling information or data

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "compile" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phasis
    -0.69
    hal
    -0.68
    otiation
    -0.63
    holes
    -0.62
    akin
    -0.61
    mington
    -0.60
    yer
    -0.60
    arat
    -0.60
    outher
    -0.59
    eat
    -0.59
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.93
     compiled
    0.86
    ãĤ¢ãĥ«
    0.84
    ãĥ¼ãĥĨãĤ£
    0.82
    ãĥį
    0.81
    ãĤ¹ãĥĪ
    0.80
    LECT
    0.77
    iton
    0.75
    ãĥĥãĥĪ
    0.75
    ãĥ³ãĤ¸
    0.71
    Act Density 0.036%

    No Known Activations