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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "speaking" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LETE
    -0.17
    ken
    -0.16
    apia
    -0.15
    pmat
    -0.15
    inte
    -0.14
    chop
    -0.14
    inho
    -0.14
    ings
    -0.14
    lete
    -0.14
    akukan
    -0.14
    POSITIVE LOGITS
     speaking
    0.35
    Speaking
    0.29
     Speaking
    0.29
    -speaking
    0.26
    spe
    0.23
     strictly
    0.23
     spoken
    0.17
    tree
    0.17
     speakers
    0.16
     purely
    0.16
    Act Density 0.030%

    No Known Activations