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

    Neuronpedia

    INDEX
    Explanations

    code elements and their properties in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /goto
    -0.16
    otton
    -0.15
    orrent
    -0.15
    plx
    -0.14
     maiden
    -0.14
    445
    -0.14
    428
    -0.14
    orton
    -0.14
    orz
    -0.14
    åĭ¤
    -0.14
    POSITIVE LOGITS
     Ly
    0.17
     K
    0.16
     unset
    0.15
    evil
    0.14
    airo
    0.14
     Legend
    0.14
    TASK
    0.14
     To
    0.14
     Fit
    0.13
    aira
    0.13
    Act Density 0.121%

    No Known Activations