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

    Neuronpedia

    INDEX
    Explanations

    words related to transitions or transformations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating transformation or change towards a particular state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inately
    -0.81
    inarily
    -0.75
    ramid
    -0.74
    bell
    -0.74
    alian
    -0.72
    erity
    -0.71
    oning
    -0.70
    ongyang
    -0.69
    orney
    -0.68
     Cran
    -0.66
    POSITIVE LOGITS
     accustomed
    1.02
     extinct
    0.95
     entangled
    0.90
     embroiled
    0.87
     aware
    0.85
     acquainted
    0.81
     disillusion
    0.81
     obsessed
    0.78
     obsolete
    0.77
     unman
    0.76
    Act Density 0.047%

    No Known Activations