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

    Neuronpedia

    INDEX
    Explanations

    contrastive expressions comparing two different scenarios or situations

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

    "On the other hand"

    np_acts-logits-general · gemini-2.0-flash

    on the other hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    figer
    -0.41
    ագրություններ
    -0.36
    Deutschland
    -0.36
     Burnham
    -0.35
    isSuccess
    -0.35
     sausage
    -0.35
     loto
    -0.35
    位
    -0.35
     Sausage
    -0.35
    rzej
    -0.34
    POSITIVE LOGITS
    omiast
    0.79
     Meanwhile
    0.79
     meanwhile
    0.75
    Meanwhile
    0.73
     Sementara
    0.71
     Sedangkan
    0.65
    Sementara
    0.65
     بينما
    0.63
    mientras
    0.63
     sedangkan
    0.63
    Act Density 0.298%

    No Known Activations