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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and contrasts in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.40
     sons
    -0.37
     de
    -0.36
     [
    -0.36
     recensement
    -0.36
     there
    -0.35
    stereotype
    -0.35
    <eos>
    -0.33
     &
    -0.33
    Filename
    -0.32
    POSITIVE LOGITS
    verwijspagina
    1.24
    EndTag
    1.01
    saraba
    0.97
     وتسجيلات
    0.92
    ?
    0.91
     Савезне
    0.90
    CloseOperation
    0.90
    تقاوى
    0.89
     يتيمه
    0.89
    ]));
    0.87
    Act Density 0.337%

    No Known Activations