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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deÅŁ
    -0.17
    raz
    -0.17
    елен
    -0.16
    rones
    -0.16
    icone
    -0.15
    adiens
    -0.15
    plusplus
    -0.15
    Idle
    -0.15
    æ´¥
    -0.15
    ffective
    -0.14
    POSITIVE LOGITS
    zan
    0.17
    olini
    0.15
    adder
    0.15
     Ward
    0.15
     planes
    0.14
    izzard
    0.14
    ua
    0.14
    ArrayType
    0.14
     Nano
    0.14
    ca
    0.14
    Act Density 0.008%

    No Known Activations