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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "made" in phrases relating to actions taken or achievements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "made" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLOSE
    -0.83
     scrimmage
    -0.69
    strip
    -0.61
     exceeded
    -0.59
    wr
    -0.58
    assis
    -0.58
     belie
    -0.56
    isphere
    -0.55
    dra
    -0.55
    hens
    -0.55
    POSITIVE LOGITS
     sure
    1.14
     strides
    1.03
     landfall
    1.01
     mistakes
    0.88
     headlines
    0.87
     excuses
    0.87
     noises
    0.86
     decisions
    0.84
     arrangements
    0.83
    hift
    0.82
    Act Density 0.136%

    No Known Activations