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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating teamwork and collaboration

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     with
    -0.76
    Iterator
    -0.68
    estate
    -0.66
     according
    -0.63
    iffe
    -0.62
    ECA
    -0.58
    lessly
    -0.58
     without
    -0.57
     Luffy
    -0.57
    ãĥĺ
    -0.57
    POSITIVE LOGITS
     same
    1.07
     utmost
    1.04
    ocratic
    1.03
     slightest
    1.01
     latter
    0.98
     highest
    0.98
    ses
    0.98
     remainder
    0.95
     lowest
    0.94
     widest
    0.94
    Act Density 0.267%

    No Known Activations