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

    Neuronpedia

    INDEX
    Explanations

    terms related to guarantees, affirmations, and common experiences or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffe
    -0.13
     addCriterion
    -0.13
    ãģ«ãģĬ
    -0.13
    åĨħãģ®
    -0.12
     dán
    -0.12
     रहन
    -0.11
    _Valid
    -0.11
     outgoing
    -0.11
     रहत
    -0.11
     reg
    -0.11
    POSITIVE LOGITS
    deÅŁ
    0.15
    podob
    0.14
     Demir
    0.13
    çĦ¡ãģĹãģ
    0.13
    olean
    0.13
    ué
    0.13
    eyse
    0.13
    gı
    0.13
    ì§Ģëħ¸
    0.13
    žen
    0.12
    Act Density 0.004%

    No Known Activations