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

    Neuronpedia

    INDEX
    Explanations

    verbs denoting a change or transition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "became" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oning
    -0.79
    inately
    -0.79
    inarily
    -0.77
    ramid
    -0.76
    enger
    -0.72
    aging
    -0.65
    orneys
    -0.64
    alian
    -0.64
    hov
    -0.63
    atching
    -0.63
    POSITIVE LOGITS
     accustomed
    0.95
     extinct
    0.93
     entangled
    0.89
     embroiled
    0.89
     disillusion
    0.83
     acquainted
    0.80
    oslav
    0.80
     aware
    0.79
     undone
    0.78
     obsessed
    0.77
    Act Density 0.051%

    No Known Activations