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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to historic or significant events or people

    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
    -0.75
    oning
    -0.73
    enger
    -0.71
    atching
    -0.71
    inately
    -0.71
    aging
    -0.68
    been
    -0.66
    otropic
    -0.66
     Glover
    -0.65
    mouth
    -0.64
    POSITIVE LOGITS
     accustomed
    0.82
     entangled
    0.81
     embroiled
    0.77
     extinct
    0.76
    oslav
    0.75
     victorious
    0.75
    ATURES
    0.75
    nces
    0.74
     ens
    0.73
     withdrawn
    0.72
    Act Density 0.047%

    No Known Activations