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

    Neuronpedia

    INDEX
    Explanations

    technical terms and commands related to computer programming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems, modules, and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rather
    -0.70
    $.
    -0.67
    é¾įå¥ij士
    -0.67
    âĹ¼
    -0.67
    fml
    -0.65
    dylib
    -0.61
    é¾įå
    -0.61
    yond
    -0.60
    urnal
    -0.59
    foreign
    -0.59
    POSITIVE LOGITS
     consists
    1.18
     comprises
    1.07
     consisted
    1.01
     contains
    0.93
     has
    0.91
     provides
    0.91
     is
    0.90
     extends
    0.87
     continues
    0.87
     begins
    0.86
    Act Density 0.675%

    No Known Activations