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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and structures within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¤
    -0.15
    aran
    -0.15
    akat
    -0.15
    oi
    -0.14
    ple
    -0.14
    .pretty
    -0.14
    terra
    -0.13
    trap
    -0.13
    arna
    -0.13
    822
    -0.13
    POSITIVE LOGITS
    âĶĺ
    0.15
    ascus
    0.15
    eos
    0.15
    ì²´
    0.15
    etheus
    0.15
    ÙĨس
    0.15
    adele
    0.15
    kinson
    0.14
     IDD
    0.14
     Ridley
    0.14
    Act Density 0.005%

    No Known Activations