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

    Neuronpedia

    INDEX
    Explanations

    phrases 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
    hal
    -0.80
    phasis
    -0.78
    holes
    -0.75
    mington
    -0.70
    aline
    -0.67
    arat
    -0.67
    egal
    -0.65
    yer
    -0.65
    orthy
    -0.65
    noon
    -0.64
    POSITIVE LOGITS
     compiled
    1.20
     compiling
    0.92
     compilation
    0.88
    ãĤ¤ãĥĪ
    0.84
    ãĤ¢ãĥ«
    0.81
    LECT
    0.79
    ographies
    0.76
    endium
    0.75
     archives
    0.74
    ãĥį
    0.72
    Act Density 0.019%

    No Known Activations