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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or similarities between different subjects or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     numberWith
    -0.65
     яко
    -0.56
    LocalizedString
    -0.55
    autés
    -0.54
     hon
    -0.54
     jScrollPane
    -0.53
    mpto
    -0.53
    reszcie
    -0.52
    Bronnen
    -0.52
     án
    -0.52
    POSITIVE LOGITS
     similarly
    1.08
     similar
    1.01
     same
    1.01
    same
    0.96
    同样的
    0.95
    Same
    0.92
     Same
    0.89
    Similarly
    0.87
    Similar
    0.87
    similar
    0.84
    Act Density 0.426%

    No Known Activations