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

    Neuronpedia

    INDEX
    Explanations

    phrases describing transactions or acquisitions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arry
    -0.78
    ichick
    -0.64
    âĢij
    -0.64
    craft
    -0.63
    ould
    -0.63
    ature
    -0.63
    anooga
    -0.62
     accompl
    -0.62
     suppose
    -0.62
    gat
    -0.62
    POSITIVE LOGITS
     same
    1.43
     entire
    1.25
     latter
    1.25
     latest
    1.22
     entirety
    1.18
     aforementioned
    1.12
     requisite
    1.11
     brunt
    1.11
    ses
    1.11
     remainder
    1.10
    Act Density 0.517%

    No Known Activations