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

    Neuronpedia

    INDEX
    Explanations

    references to historical events or a person's personal history

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events or the concept of the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.78
    wagon
    -0.75
    shapeshifter
    -0.73
    hyde
    -0.67
    mand
    -0.66
    lee
    -0.64
    NEY
    -0.64
    ately
    -0.63
    Downloadha
    -0.63
    zhen
    -0.63
    POSITIVE LOGITS
    ebin
    1.55
    iche
    1.17
     tense
    1.05
    ures
    1.01
    ime
    1.00
    orate
    0.92
    imes
    0.91
     generations
    0.84
    oral
    0.80
    ure
    0.77
    Act Density 0.029%

    No Known Activations