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

    Neuronpedia

    INDEX
    Explanations

    articles and determiners in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quite a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mlink
    -0.49
     unconditionally
    -0.46
     nakalista
    -0.44
     atras
    -0.43
    AutoScaleMode
    -0.43
     становника
    -0.42
    MethodImpl
    -0.41
    ivka
    -0.41
     ویکی
    -0.40
     Taktlose
    -0.40
    POSITIVE LOGITS
    ThroughAttribute
    0.62
    <bos>
    0.62
     Interesting
    0.54
     Considerable
    0.52
    incredible
    0.52
     tremendous
    0.51
    NameInMap
    0.51
    很多的
    0.51
    Nice
    0.50
    bitField
    0.50
    Act Density 0.011%

    No Known Activations