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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code patterns involving functions and syntax

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swast
    -0.86
     Whole
    -0.85
    ãĥŃ
    -0.79
    Shape
    -0.73
     Stick
    -0.73
    geist
    -0.73
     Streets
    -0.73
    Wo
    -0.72
     Hearth
    -0.70
     Ghosts
    -0.69
    POSITIVE LOGITS
    ptin
    0.93
    imoto
    0.89
    riber
    0.87
    ani
    0.85
    iaz
    0.84
    fff
    0.83
    amiya
    0.82
    absor
    0.81
    iola
    0.79
    ription
    0.79
    Act Density 0.454%

    No Known Activations