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

    Neuronpedia

    INDEX
    Explanations

    instances of temporal phrases indicating frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTable
    -0.14
    paged
    -0.14
    olleyError
    -0.14
    itti
    -0.14
    ijing
    -0.14
    egan
    -0.14
    orio
    -0.14
    .scalablytyped
    -0.14
    raquo
    -0.14
     воÑĤ
    -0.13
    POSITIVE LOGITS
     blue
    0.23
     Blue
    0.22
    Blue
    0.18
     BLUE
    0.18
    blue
    0.18
     so
    0.18
    -blue
    0.18
     often
    0.18
     tanto
    0.17
    rule
    0.17
    Act Density 0.016%

    No Known Activations