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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming-related keywords

    oai_token-act-pair · gpt-3.5-turbo

    programming keywords and elements related to code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agall
    -0.88
    bringer
    -0.76
    rored
    -0.73
    agra
    -0.71
    jriwal
    -0.68
    angers
    -0.68
    )].
    -0.64
    anger
    -0.64
    abouts
    -0.64
    Redd
    -0.63
    POSITIVE LOGITS
     ns
    0.92
     foo
    0.84
     WATCHED
    0.84
     java
    0.82
     {
    0.74
    <?
    0.74
     fn
    0.73
     namespace
    0.72
     ::
    0.70
     hello
    0.69
    Act Density 0.081%

    No Known Activations