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

    Neuronpedia

    INDEX
    Explanations

    references to programming constructs and assertions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     |↵↵
    -0.40
    ↵↵
    -0.29
    ”ãĢĤ↵↵
    -0.28
    >↵↵
    -0.28
    "↵↵
    -0.27
    .↵↵
    -0.27
    ãĢı↵↵
    -0.27
    !↵↵
    -0.27
    ãĢij↵↵
    -0.27
    ...↵↵
    -0.27
    POSITIVE LOGITS
    ");}↵
    0.20
    ();}↵
    0.19
    ";}↵
    0.18
    ***/↵
    0.17
    ){}↵
    0.17
    );}↵
    0.16
    ."""↵
    0.16
    .*/↵
    0.16
    "});↵
    0.16
    !';↵
    0.16
    Act Density 0.282%

    No Known Activations