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

    Neuronpedia

    INDEX
    Explanations

    instances where something undergoes a transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "become" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inarily
    -0.75
    inately
    -0.75
    osite
    -0.69
    ramid
    -0.69
    oning
    -0.68
    orney
    -0.68
    alian
    -0.67
    atching
    -0.67
    otropic
    -0.66
    bell
    -0.64
    POSITIVE LOGITS
     accustomed
    0.96
     entangled
    0.89
     extinct
    0.84
     embroiled
    0.79
    nces
    0.79
     disillusion
    0.78
     undone
    0.78
     acquainted
    0.77
     obsolete
    0.76
     unman
    0.76
    Act Density 0.047%

    No Known Activations