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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zel
    -0.15
     Locker
    -0.15
    executable
    -0.15
    è©
    -0.14
    tein
    -0.14
    608
    -0.13
     Hath
    -0.13
    ikel
    -0.13
    vsp
    -0.13
     Morr
    -0.13
    POSITIVE LOGITS
    onet
    0.20
     overnight
    0.16
    ebi
    0.16
    Äįást
    0.15
    using
    0.14
     Overnight
    0.14
    adle
    0.14
     Till
    0.14
    owan
    0.13
     campaigning
    0.13
    Act Density 0.005%

    No Known Activations