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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing critique or strong opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of being "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sembly
    -0.88
     GOODMAN
    -0.74
    odies
    -0.66
     Users
    -0.63
     Emin
    -0.63
     Funds
    -0.63
    aders
    -0.62
     colleg
    -0.61
     Yard
    -0.60
    plings
    -0.59
    POSITIVE LOGITS
    edly
    0.73
     rejection
    0.71
    stand
    0.68
    Repe
    0.68
    lined
    0.67
     lie
    0.66
    Ign
    0.65
    Latin
    0.65
    Country
    0.64
    butt
    0.63
    Act Density 0.076%

    No Known Activations