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

    Neuronpedia

    INDEX
    Explanations

    code snippets with a focus on manipulating collections or aggregates

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and periods in code content, indicating the structure of programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.82
     conflic
    -0.82
     glim
    -0.81
    quished
    -0.81
     behavi
    -0.81
     mosqu
    -0.79
    vernment
    -0.79
     therap
    -0.75
     quo
    -0.75
     enthusi
    -0.74
    POSITIVE LOGITS
    mk
    0.82
    ini
    0.75
     Stub
    0.71
     Get
    0.69
    default
    0.68
    local
    0.67
     _
    0.67
     mk
    0.66
    get
    0.66
    html
    0.66
    Act Density 0.041%

    No Known Activations