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

    Neuronpedia

    INDEX
    Explanations

    prepositions denoting movement or direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "out" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Berry
    -0.59
     bidder
    -0.56
     Conservatives
    -0.55
    Availability
    -0.54
    istani
    -0.54
    avorite
    -0.51
     arrang
    -0.51
    YL
    -0.50
    ãĥĩãĤ£
    -0.50
    BILITIES
    -0.49
    POSITIVE LOGITS
    wards
    1.39
    stretched
    1.31
    fitted
    1.28
    ta
    1.14
     onto
    1.06
     of
    1.02
    posts
    0.99
    worn
    0.95
    cro
    0.93
    fitting
    0.88
    Act Density 0.093%

    No Known Activations