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

    Neuronpedia

    INDEX
    Explanations

    references to boundaries or gaps in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESH
    -0.16
    аÑĢÑĮ
    -0.16
    phia
    -0.15
    еÑĪ
    -0.15
    duce
    -0.15
    Ú©Ùħ
    -0.14
    pty
    -0.14
    orio
    -0.14
    ØŃÙĬ
    -0.14
    áº
    -0.13
    POSITIVE LOGITS
    eras
    0.16
    azon
    0.14
    enville
    0.14
    oren
    0.14
    oreferrer
    0.14
    .scalablytyped
    0.14
     Cove
    0.14
    582
    0.14
    us
    0.14
     of
    0.14
    Act Density 0.241%

    No Known Activations