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

    Neuronpedia

    INDEX
    Explanations

    phrases that assert the existence or presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¨
    -0.15
    ÐĦ
    -0.15
    sehen
    -0.14
    arger
    -0.14
    itest
    -0.14
    ampaign
    -0.14
    217
    -0.14
     رÙħز
    -0.14
    à¹īาหà¸Ļ
    -0.14
    .Experimental
    -0.14
    POSITIVE LOGITS
    ÙĪدÛĮ
    0.14
     weakness
    0.14
    osa
    0.13
    abo
    0.13
     Bash
    0.13
     Dew
    0.13
    _INCLUDED
    0.13
     Virgin
    0.13
    nts
    0.13
     Hong
    0.13
    Act Density 0.253%

    No Known Activations