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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing permission or approval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hani
    -0.80
    marine
    -0.79
    ulhu
    -0.75
    raped
    -0.70
    riber
    -0.65
    ocrat
    -0.64
    ulator
    -0.62
    enegger
    -0.61
    leneck
    -0.61
    hunt
    -0.60
    POSITIVE LOGITS
    AY
    0.91
    lahoma
    0.83
     okay
    0.69
     HOME
    0.68
     alright
    0.66
     bye
    0.65
    terday
    0.65
     ok
    0.65
     margin
    0.64
     margins
    0.64
    Act Density 0.018%

    No Known Activations