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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes in statistics and comparisons in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zwar
    -0.17
    agen
    -0.16
     successors
    -0.15
    isel
    -0.15
    uet
    -0.14
    (rawValue
    -0.14
    677
    -0.14
    ople
    -0.13
    ute
    -0.13
    iosa
    -0.13
    POSITIVE LOGITS
     corresponding
    0.71
     equally
    0.59
     correspond
    0.56
     Correspond
    0.52
     corres
    0.49
     correspondent
    0.46
     similarly
    0.44
     corresponds
    0.41
     ÑģооÑĤвеÑĤÑģÑĤв
    0.40
     entsprech
    0.38
    Act Density 0.241%

    No Known Activations