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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bef
    -0.16
     Might
    -0.15
    thinkable
    -0.15
    .assertThat
    -0.14
    nown
    -0.14
    ever
    -0.14
    ër
    -0.14
     atIndex
    -0.14
    öt
    -0.13
    avier
    -0.13
    POSITIVE LOGITS
     far
    0.28
     much
    0.23
    far
    0.20
     long
    0.20
     corn
    0.19
    ides
    0.19
    long
    0.19
     soon
    0.19
     oppose
    0.18
    much
    0.17
    Act Density 0.085%

    No Known Activations