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

    Neuronpedia

    INDEX
    Explanations

    names and terms associated with entities or organizations in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    非常的
    -0.85
     diatas
    -0.85
     içerisinde
    -0.78
     می‌باشد
    -0.76
    十分的
    -0.75
     didalam
    -0.72
     אשר
    -0.71
    Whilst
    -0.69
     içeris
    -0.68
     अनुसार
    -0.67
    POSITIVE LOGITS
    ftagPool
    0.89
    +#+#
    0.88
    NameInMap
    0.81
    <?
    0.80
     freilich
    0.79
     beginnetje
    0.77
     henvisninger
    0.77
     guère
    0.77
    UnitTesting
    0.77
    LookAnd
    0.76
    Act Density 0.469%

    No Known Activations