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

    Neuronpedia

    INDEX
    Explanations

    the word "Notice" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rose
    -0.17
    istry
    -0.16
    soever
    -0.16
    sWith
    -0.15
    ago
    -0.14
    teenth
    -0.14
    lover
    -0.14
    SSIP
    -0.14
    olver
    -0.14
     Glover
    -0.14
    POSITIVE LOGITS
    ably
    0.34
    able
    0.23
    ously
    0.21
    ables
    0.21
    ability
    0.18
    ering
    0.18
    lessly
    0.18
    edom
    0.17
    ment
    0.17
    abl
    0.17
    Act Density 0.019%

    No Known Activations