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

    Neuronpedia

    INDEX
    Explanations

    instances of "even" used to emphasize a surprising or noteworthy point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     versa
    -0.66
    tagHelperRunner
    -0.62
    __':
    -0.60
    }]);
    -0.57
    GenerationType
    -0.54
    UPAC
    -0.54
    extAlignment
    -0.53
     combineReducers
    -0.52
     venido
    -0.51
     Commandant
    -0.50
    POSITIVE LOGITS
     וגם
    0.78
     sekal
    0.74
     even
    0.72
    Даже
    0.67
    віть
    0.64
    Even
    0.64
    EVEN
    0.62
     Even
    0.59
     asti
    0.58
     nawet
    0.57
    Act Density 0.194%

    No Known Activations