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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jadx
    -0.15
    afi
    -0.14
    ipple
    -0.14
    óc
    -0.14
    aler
    -0.14
    quer
    -0.14
    ecess
    -0.13
    bakan
    -0.13
    ipples
    -0.13
     Shak
    -0.13
    POSITIVE LOGITS
     talking
    0.32
     Talking
    0.28
    Talking
    0.25
     moving
    0.20
     Moving
    0.20
     talks
    0.20
    CAP
    0.19
    Caption
    0.19
     Sources
    0.19
    moving
    0.18
    Act Density 0.004%

    No Known Activations