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

    Neuronpedia

    INDEX
    Explanations

    code-related mechanisms or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oso
    -0.15
    losures
    -0.15
    å¿Ĺ
    -0.14
    opathic
    -0.14
    нÑĮ
    -0.14
    ess
    -0.14
     nond
    -0.14
     borders
    -0.14
    erk
    -0.13
    isiyle
    -0.13
    POSITIVE LOGITS
    лÑĥг
    0.19
    ugen
    0.16
    uger
    0.15
    olest
    0.15
    uga
    0.14
     peril
    0.14
    oÄį
    0.14
    roker
    0.14
    ROLLER
    0.14
    öl
    0.13
    Act Density 0.020%

    No Known Activations