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

    Neuronpedia

    INDEX
    Explanations

    donation amounts stated in specific ranges

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or amounts with a focus on "more" and "less."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµ
    -0.70
    CAP
    -0.69
    ãĤ¦ãĤ¹
    -0.69
     HIP
    -0.68
    crime
    -0.64
    ©¶æ
    -0.63
     Ike
    -0.62
     Ragnarok
    -0.62
    Austral
    -0.62
     Turing
    -0.61
    POSITIVE LOGITS
    inence
    0.72
    agonal
    0.72
     depending
    0.72
     thereof
    0.69
     intact
    0.69
     equivalent
    0.67
    inction
    0.67
     recognized
    0.66
    urbed
    0.66
    inent
    0.66
    Act Density 0.038%

    No Known Activations