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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant events or changes in someone's life

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "became."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inarily
    -0.76
    been
    -0.72
    inately
    -0.70
    otropic
    -0.69
    atching
    -0.68
    alian
    -0.67
    oning
    -0.67
    enger
    -0.65
    ramid
    -0.64
    aging
    -0.64
    POSITIVE LOGITS
    oslav
    0.87
     accustomed
    0.85
     entangled
    0.80
    nces
    0.80
     extinct
    0.77
     embroiled
    0.76
     undone
    0.75
    EStream
    0.74
     disillusion
    0.73
    ATURES
    0.73
    Act Density 0.041%

    No Known Activations