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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.62
     itſelf
    -0.59
     ―――――
    -0.59
     leaſt
    -0.58
     myſelf
    -0.57
     himſelf
    -0.53
     Boven
    -0.52
     uſed
    -0.52
     Pamph
    -0.52
     becauſe
    -0.51
    POSITIVE LOGITS
    <eos>
    0.99
    ↵↵
    0.81
    ]--;
    0.61
    dstuk
    0.58
     ujednoznacz
    0.57
    AccessorTable
    0.57
    </b>
    0.55
    ]='\
    0.55
    BeginContext
    0.55
    '])){
    0.53
    Act Density 0.708%

    No Known Activations