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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer science and programming

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to education standards and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kers
    -0.71
     Ambrose
    -0.69
     tyr
    -0.69
     Jord
    -0.68
     Sov
    -0.66
     Bris
    -0.66
     skelet
    -0.65
    umm
    -0.62
     Ferr
    -0.62
    eah
    -0.61
    POSITIVE LOGITS
    Saharan
    0.80
    ervative
    0.77
    igger
    0.75
    âĦ¢
    0.73
    ervatives
    0.71
    ®
    0.70
    tein
    0.69
    èĢħ
    0.68
    xual
    0.67
    quished
    0.67
    Act Density 0.353%

    No Known Activations