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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to choices and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    миÑĤ
    -0.18
    ATTRIBUTE
    -0.15
    elmet
    -0.15
    åĿĬ
    -0.14
     Fade
    -0.14
    ²
    -0.14
    屬
    -0.14
    _supply
    -0.14
    enheim
    -0.14
    _FREQUENCY
    -0.14
    POSITIVE LOGITS
     host
    0.15
     annex
    0.14
     fond
    0.14
     sort
    0.14
    adle
    0.13
    occo
    0.13
     talent
    0.13
     ç¥
    0.13
     ëĮĢ
    0.13
    Host
    0.13
    Act Density 0.004%

    No Known Activations