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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that end with punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uz
    -0.15
    clin
    -0.15
    cpy
    -0.15
    ká
    -0.15
    bbe
    -0.15
    wor
    -0.14
    udem
    -0.14
    bere
    -0.14
    á»±c
    -0.14
    olec
    -0.14
    POSITIVE LOGITS
    ÑĮ
    0.15
    anse
    0.15
    åĿĬ
    0.14
    kas
    0.13
    ÃĹ↵↵
    0.13
    elter
    0.13
     Boeh
    0.13
    IMUM
    0.13
     invert
    0.12
     ceasefire
    0.12
    Act Density 0.563%

    No Known Activations