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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantifiable measures or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apers
    -0.17
    ahi
    -0.17
    .tw
    -0.15
    pard
    -0.15
    mans
    -0.15
     Madden
    -0.14
    raud
    -0.14
     Bacon
    -0.14
    تÙģ
    -0.14
    Ĥ
    -0.14
    POSITIVE LOGITS
    åĪ°
    0.21
     kepada
    0.21
     unto
    0.20
    eer
    0.20
     to
    0.19
    ToSelector
    0.18
    ToBounds
    0.18
    åĪ°äºĨ
    0.17
     اÙĦÙī
    0.17
    bersome
    0.17
    Act Density 0.012%

    No Known Activations