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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to programming attributes and methods in structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    missive
    -0.14
    ifold
    -0.14
    igon
    -0.13
    ewhat
    -0.13
    nip
    -0.13
    -pad
    -0.13
    allen
    -0.12
    brig
    -0.12
    pad
    -0.12
    porn
    -0.12
    POSITIVE LOGITS
     something
    0.18
     somehow
    0.17
     etc
    0.16
     some
    0.16
     another
    0.16
     jerk
    0.16
    omething
    0.16
    something
    0.15
     somewhere
    0.15
     somew
    0.14
    Act Density 0.307%

    No Known Activations