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

    Neuronpedia

    INDEX
    Explanations

    words related to breaks or pauses in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abcdef
    -0.17
     Mile
    -0.15
    ----</
    -0.14
    گار
    -0.13
     Patron
    -0.13
     Milk
    -0.13
    Indexed
    -0.13
    esson
    -0.13
    биÑĤ
    -0.13
    CAF
    -0.13
    POSITIVE LOGITS
    esis
    0.18
    596
    0.16
    ughs
    0.15
    ières
    0.15
    aal
    0.15
    okus
    0.15
    592
    0.15
    ieg
    0.15
    Buffers
    0.15
    å¹³æĪIJ
    0.15
    Act Density 0.005%

    No Known Activations