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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating updates or forthcoming information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     artık
    -0.19
    uraa
    -0.16
    ÙĪسط
    -0.15
     maintenant
    -0.15
    celik
    -0.15
    now
    -0.14
    finally
    -0.14
     decades
    -0.14
    _YUV
    -0.14
     Nowadays
    -0.13
    POSITIVE LOGITS
     later
    0.33
    later
    0.27
     shortly
    0.27
     soon
    0.25
     updates
    0.24
     nearer
    0.23
    Later
    0.23
     closer
    0.23
     Later
    0.23
     Soon
    0.21
    Act Density 0.108%

    No Known Activations