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

    Neuronpedia

    INDEX
    Explanations

    phrases related to installation or implementation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "installed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sem
    -0.89
    wer
    -0.77
     Hague
    -0.76
    houn
    -0.74
    hon
    -0.73
    emic
    -0.72
    step
    -0.70
    Sullivan
    -0.69
    ber
    -0.68
    king
    -0.68
    POSITIVE LOGITS
     installed
    1.33
     installs
    1.09
     installations
    1.08
     installation
    1.07
     install
    1.01
     installing
    0.95
     uninstall
    0.88
     eleph
    0.87
     destro
    0.86
    installed
    0.83
    Act Density 0.010%

    No Known Activations