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

    Neuronpedia

    INDEX
    Explanations

    high-frequency function words and terms related to conditions or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izu
    -0.17
    crollView
    -0.16
    dum
    -0.16
    ocha
    -0.15
    ruba
    -0.15
    radu
    -0.15
    ijo
    -0.15
    çĶ
    -0.14
    rubu
    -0.14
    idar
    -0.14
    POSITIVE LOGITS
     whether
    0.21
     tern
    0.15
    whether
    0.15
    677
    0.15
    Whether
    0.15
    ate
    0.15
     detail
    0.15
     Whether
    0.15
    ethe
    0.15
    stance
    0.14
    Act Density 0.003%

    No Known Activations