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

    Neuronpedia

    INDEX
    Explanations

    words related to adjectives and descriptive phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oples
    -0.17
    plusplus
    -0.17
    ify
    -0.15
    elden
    -0.15
     misc
    -0.14
    pong
    -0.14
    Ñľ
    -0.14
    oning
    -0.14
    ritten
    -0.14
     Trouble
    -0.14
    POSITIVE LOGITS
    atus
    0.17
    icide
    0.15
     Candle
    0.14
    /***************************************************************************↵
    0.14
    hurst
    0.14
    osate
    0.14
    Insensitive
    0.14
    åĸ
    0.14
    æĶ
    0.14
    ScreenWidth
    0.14
    Act Density 0.291%

    No Known Activations