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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and the word 'and' used abundantly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ego
    -0.16
    elters
    -0.15
    縮
    -0.15
    Assignable
    -0.14
    plan
    -0.14
    ecs
    -0.14
     loc
    -0.14
     Pag
    -0.13
    sters
    -0.13
     BM
    -0.13
    POSITIVE LOGITS
    -sidebar
    0.16
    æ½®
    0.16
    FY
    0.15
    á»ijc
    0.15
    że
    0.14
    reopen
    0.14
    hw
    0.14
    ozor
    0.14
    iron
    0.14
     Majority
    0.14
    Act Density 0.112%

    No Known Activations