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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "opinion."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Friends
    -0.17
    ymoon
    -0.17
    Friends
    -0.16
    ocked
    -0.16
    ordin
    -0.16
     accent
    -0.15
    ynchron
    -0.15
    urance
    -0.15
    Beam
    -0.15
    friends
    -0.15
    POSITIVE LOGITS
    inions
    0.30
    ulent
    0.27
    inion
    0.26
    POSITE
    0.24
    portunity
    0.24
    encv
    0.23
    ulence
    0.23
    posite
    0.21
    ération
    0.21
    ium
    0.20
    Act Density 0.013%

    No Known Activations