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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance, such as "the real issue here" or "an important part here."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the significance or implications of issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailability
    -0.65
    CLASSIFIED
    -0.62
    gettable
    -0.61
    dding
    -0.60
     womb
    -0.57
    ustomed
    -0.56
    itted
    -0.56
     ];
    -0.54
    inka
    -0.53
    Done
    -0.53
    POSITIVE LOGITS
     involves
    1.43
     relates
    1.38
     is
    1.35
     boils
    1.34
     revolves
    1.34
     arises
    1.22
     rests
    1.21
     stems
    1.20
     consists
    1.20
     depends
    1.16
    Act Density 0.252%

    No Known Activations