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

    Neuronpedia

    INDEX
    Explanations

    words related to pronouns and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bell
    -0.19
    ture
    -0.17
    cas
    -0.15
    509
    -0.14
     Whisper
    -0.14
    een
    -0.14
    ÑĩаÑģ
    -0.14
    rette
    -0.14
    fony
    -0.14
    u
    -0.14
    POSITIVE LOGITS
    ounced
    0.34
    ouns
    0.23
    unciation
    0.23
    ouncing
    0.23
    ounces
    0.22
    ouncements
    0.22
     pron
    0.20
     Pron
    0.19
    ounce
    0.19
    ájem
    0.17
    Act Density 0.007%

    No Known Activations