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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax elements in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     congratulations
    -1.40
    Congratulations
    -1.34
     Congratulations
    -1.32
     congrats
    -1.24
     Congrats
    -1.22
    Congrats
    -1.20
     congratulate
    -1.12
    congratulations
    -1.07
     congrat
    -1.07
     congratulated
    -0.98
    POSITIVE LOGITS
     _
    0.97
     _,
    0.93
     _)
    0.91
     _:
    0.84
    (_
    0.82
    _,
    0.81
     &_
    0.80
    ,_
    0.76
    [_
    0.75
     *_
    0.72
    Act Density 0.258%

    No Known Activations