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

    Neuronpedia

    INDEX
    Explanations

    phrases about duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     for
    -0.17
     haste
    -0.15
    ese
    -0.15
     за
    -0.14
    ick
    -0.14
    atis
    -0.14
    ses
    -0.14
    svc
    -0.14
    ivism
    -0.14
     voor
    -0.14
    POSITIVE LOGITS
     longer
    0.27
     Longer
    0.22
    liÄŁine
    0.21
     dÃłi
    0.19
    -long
    0.18
    oyer
    0.18
     period
    0.18
    onder
    0.17
     longest
    0.17
    rost
    0.16
    Act Density 0.081%

    No Known Activations