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

    Neuronpedia

    INDEX
    Explanations

    expressions of expertise and performance-related attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grant
    -0.15
    rita
    -0.15
    γκο
    -0.14
    hua
    -0.14
    \Unit
    -0.13
    \grid
    -0.13
    Ĺi
    -0.13
    logen
    -0.13
    itra
    -0.13
    olin
    -0.13
    POSITIVE LOGITS
    istani
    0.16
    жи
    0.14
    osi
    0.14
    ict
    0.14
     boyfriend
    0.14
    ich
    0.14
    GP
    0.14
    keit
    0.14
    icari
    0.13
    baugh
    0.13
    Act Density 0.321%

    No Known Activations