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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific character or sequence in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.15
    oration
    -0.14
    968
    -0.14
    ãĤĥ
    -0.14
    284
    -0.14
    globals
    -0.14
     маÑĪ
    -0.14
    806
    -0.14
    care
    -0.13
    ç«ĭãģ¦
    -0.13
    POSITIVE LOGITS
     literature
    0.22
     Literature
    0.22
     ÐĽÐ¸ÑĤ
    0.21
    æĸĩçĮ®
    0.20
     bibliography
    0.20
    Liter
    0.20
     bibli
    0.19
     liter
    0.18
     Liter
    0.18
     foot
    0.18
    Act Density 0.020%

    No Known Activations