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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future events or upcoming releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansi
    -0.16
    عا
    -0.15
    ancel
    -0.14
    веÑī
    -0.14
    à¹Ħà¸Ľ
    -0.14
    تاب
    -0.14
    uzey
    -0.13
    зв
    -0.13
    aise
    -0.13
    entai
    -0.13
    POSITIVE LOGITS
     soon
    0.33
     attractions
    0.33
     Soon
    0.32
    Soon
    0.31
     Attr
    0.31
    soon
    0.30
     attraction
    0.27
    Attr
    0.25
    ling
    0.24
    led
    0.23
    Act Density 0.027%

    No Known Activations