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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a comparative or superlative degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.71
     dand
    -0.68
    Ouch
    -0.66
     поводу
    -0.63
    ".
    -0.62
    arote
    -0.62
     Caballero
    -0.62
    !".
    -0.61
     Blonde
    -0.60
     Jungle
    -0.60
    POSITIVE LOGITS
     greater
    2.22
    Greater
    2.18
     Greater
    2.14
    greater
    2.12
    GREATER
    1.81
    greatest
    1.54
     greatest
    1.53
    Greatest
    1.45
     Greatest
    1.38
     maggiore
    1.08
    Act Density 0.060%

    No Known Activations