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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency and repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    928
    -0.15
    ÑĪин
    -0.15
    sen
    -0.15
    .XR
    -0.15
    heed
    -0.14
    Foreground
    -0.14
     TRACE
    -0.14
    tion
    -0.14
    eping
    -0.14
    ka
    -0.13
    POSITIVE LOGITS
    alled
    0.20
    缮ãģ®
    0.16
     Rooney
    0.16
    opard
    0.15
    RefCount
    0.15
    æľºä¼ļ
    0.15
    Repeated
    0.15
    缮
    0.14
    unga
    0.14
    .nih
    0.14
    Act Density 0.083%

    No Known Activations