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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eras
    -0.16
    umd
    -0.15
    ewise
    -0.14
    kiye
    -0.14
    asm
    -0.14
    anus
    -0.14
    eldom
    -0.14
    eros
    -0.14
    udit
    -0.14
    anik
    -0.14
    POSITIVE LOGITS
    shall
    0.19
     shall
    0.18
     at
    0.18
     quite
    0.17
     in
    0.17
     according
    0.16
     like
    0.16
     Shall
    0.16
     contrary
    0.16
     gulp
    0.16
    Act Density 0.051%

    No Known Activations