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

    Neuronpedia

    INDEX
    Explanations

    phrases related to timing and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     new
    -0.43
     free
    -0.41
    a
    -0.41
    8
    -0.41
     étrangère
    -0.40
     Free
    -0.39
     helft
    -0.38
     hundred
    -0.38
     thousand
    -0.38
    public
    -0.38
    POSITIVE LOGITS
     Timing
    1.26
     timings
    1.22
     timing
    1.22
    Timing
    1.16
    timing
    1.14
    Timings
    0.94
    timed
    0.92
     timed
    0.89
     timelines
    0.83
     Timeline
    0.82
    Act Density 0.007%

    No Known Activations