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

    Neuronpedia

    INDEX
    Explanations

    contrasts in statements or comparisons involving traditional vs. digital contexts

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

    contrasting statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.55
    autique
    -0.49
    avares
    -0.48
     EClass
    -0.47
     Signalez
    -0.47
    енча
    -0.46
    principalColumn
    -0.45
     Zw
    -0.45
    hartt
    -0.44
     NSCoder
    -0.44
    POSITIVE LOGITS
     unlike
    0.69
    unlike
    0.68
    Unlike
    0.67
     Unlike
    0.65
     отличие
    0.43
     dissimilar
    0.42
    異なります
    0.41
    TypedDataSet
    0.41
     hoeft
    0.40
     برخ
    0.40
    Act Density 0.048%

    No Known Activations