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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ranking or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    za
    -0.18
    inic
    -0.16
    ansen
    -0.16
    er
    -0.15
    top
    -0.15
    rna
    -0.15
    ients
    -0.15
    esses
    -0.15
    hips
    -0.14
    ÏĨι
    -0.14
    POSITIVE LOGITS
    -notch
    0.37
    pling
    0.34
    -rated
    0.32
    -tier
    0.31
    most
    0.30
     notch
    0.29
    ographical
    0.28
    ography
    0.27
     tier
    0.26
    -flight
    0.26
    Act Density 0.023%

    No Known Activations