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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :animated
    -0.15
     uchar
    -0.15
    ermen
    -0.14
    ure
    -0.14
    uchi
    -0.14
    OC
    -0.14
    ucc
    -0.14
    echa
    -0.14
    usan
    -0.13
    ¤
    -0.13
    POSITIVE LOGITS
    quot
    0.17
    ynch
    0.17
    oola
    0.16
    ystate
    0.15
     quot
    0.15
    alus
    0.15
    .DropDown
    0.15
     Rhodes
    0.14
    vant
    0.14
    ched
    0.14
    Act Density 0.126%

    No Known Activations