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

    Neuronpedia

    INDEX
    Explanations

    references to periods of absence or breaks in activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achel
    -0.16
    ãĤįãģĨ
    -0.16
    expo
    -0.15
    oom
    -0.14
    _ALREADY
    -0.14
     Undo
    -0.14
     Already
    -0.14
     Invalid
    -0.14
    Already
    -0.14
    676
    -0.13
    POSITIVE LOGITS
     hiatus
    0.38
     gap
    0.25
     absence
    0.24
     pause
    0.24
    gap
    0.23
    -gap
    0.23
    pause
    0.23
    Gap
    0.22
    Pause
    0.22
     gaps
    0.22
    Act Density 0.205%

    No Known Activations