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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questions and their corresponding answers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igi
    -0.17
    ------+------+
    -0.15
    ̣
    -0.15
    enez
    -0.15
    akis
    -0.14
    quez
    -0.14
    Ñijм
    -0.14
    ernal
    -0.14
    wolf
    -0.14
    ewis
    -0.14
    POSITIVE LOGITS
    phone
    0.16
    nable
    0.15
     truth
    0.15
    idual
    0.15
    stell
    0.15
    affen
    0.15
    /address
    0.14
    IFS
    0.14
    aries
    0.14
    hip
    0.14
    Act Density 0.051%

    No Known Activations