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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to coding and programming

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statistical likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.62
    igers
    -0.61
    instead
    -0.58
     guiName
    -0.57
    allery
    -0.57
     âĵĺ
    -0.57
    ulnerable
    -0.56
    atta
    -0.54
    atile
    -0.53
    rift
    -0.53
    POSITIVE LOGITS
     hindsight
    0.83
     coincidence
    0.79
    })
    0.76
     pse
    0.75
     phr
    0.72
    )}
    0.72
     retrospect
    0.69
     circumstance
    0.67
     conjecture
    0.66
     persuasion
    0.65
    Act Density 1.212%

    No Known Activations