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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "speaking" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apia
    -0.17
    ÄĽj
    -0.16
    ims
    -0.15
    Copyright
    -0.15
    opyright
    -0.15
    uales
    -0.14
    pto
    -0.14
     Copyright
    -0.14
    idia
    -0.14
    eterangan
    -0.13
    POSITIVE LOGITS
     speaking
    0.35
     Speaking
    0.32
    Speaking
    0.30
    spe
    0.25
    -speaking
    0.24
     strictly
    0.23
    strict
    0.19
     spoken
    0.18
     talking
    0.18
     speak
    0.18
    Act Density 0.017%

    No Known Activations