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

    Neuronpedia

    INDEX
    Explanations

    negative phrases related to errors or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.94
    AnchorTagHelper
    -0.92
    ⓧ
    -0.88
     ―――――
    -0.82
    ContentAsync
    -0.79
    .*")]
    -0.77
     ་་
    -0.77
     Phaser
    -0.74
     @}
    -0.73
    sizeCache
    -0.73
    POSITIVE LOGITS
     
    0.73
    0.45
    ()[
    0.44
    <bos>
    0.43
    nitts
    0.43
     planètes
    0.43
    thalle
    0.41
    Mailbox
    0.41
    \_
    0.41
    lott
    0.41
    Act Density 0.052%
    No Known Activations