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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "too" followed by an adjective or verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express limitations or excessive amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.78
    scribe
    -0.68
    iamond
    -0.67
    USS
    -0.64
    ffer
    -0.63
    ief
    -0.63
    clud
    -0.62
    FOX
    -0.61
    amines
    -0.61
    ciation
    -0.61
    POSITIVE LOGITS
    too
    2.03
     too
    1.88
     Too
    1.87
    Too
    1.83
     insufficient
    1.41
     overly
    1.16
     excessively
    1.13
     unnecessarily
    1.09
     careless
    1.07
     inadequate
    1.06
    Act Density 0.172%

    No Known Activations