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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or transitions in narrative descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wheel
    -0.15
    adium
    -0.15
    UNCT
    -0.15
    оÑĩно
    -0.14
    agon
    -0.14
    ervo
    -0.14
     behalf
    -0.14
    gebra
    -0.14
    μά
    -0.14
    ingo
    -0.13
    POSITIVE LOGITS
    bred
    0.25
    ogh
    0.19
    786
    0.18
    -out
    0.18
     suá»ijt
    0.18
    puts
    0.18
    s
    0.18
    aus
    0.17
    ought
    0.16
    enger
    0.16
    Act Density 0.113%

    No Known Activations