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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific punctuation and structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARK
    -0.14
    ansom
    -0.14
    emiz
    -0.13
    ØŃداث
    -0.13
    noop
    -0.13
    alk
    -0.13
    Intialized
    -0.13
     ked
    -0.13
    itive
    -0.12
    .Addr
    -0.12
    POSITIVE LOGITS
    以åıĬ
    0.31
    ï¼Į以åıĬ
    0.29
     plus
    0.28
     ainsi
    0.26
     sowie
    0.26
     oraz
    0.24
    plus
    0.24
    è¿ĺæľī
    0.20
     followed
    0.20
    along
    0.20
    Act Density 0.276%

    No Known Activations