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

    Neuronpedia

    INDEX
    Explanations

    articles that end with the token "TO"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "TO" that likely indicates a reference to a location or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ens
    -0.68
    busters
    -0.65
    itance
    -0.62
    groups
    -0.61
    written
    -0.60
    lished
    -0.60
    space
    -0.59
    vertis
    -0.59
    trak
    -0.59
     Courage
    -0.58
    POSITIVE LOGITS
    OME
    1.12
    KEN
    1.06
    TO
    1.05
    YA
    0.92
    GA
    0.91
    BY
    0.88
    OF
    0.86
    OL
    0.85
    OM
    0.85
    YC
    0.82
    Act Density 0.009%

    No Known Activations