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

    Neuronpedia

    INDEX
    Explanations

    words related to historical eras

    oai_token-act-pair · gpt-3.5-turbo

    references to distinct periods or eras in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acts
    -0.79
    lations
    -0.75
     drawer
    -0.75
    atem
    -0.74
    pel
    -0.70
    ournals
    -0.69
    inently
    -0.68
    Ĥ¬
    -0.68
    portion
    -0.67
    gments
    -0.66
    POSITIVE LOGITS
     era
    0.91
    icals
    0.86
     epoch
    0.83
     UTC
    0.83
     Era
    0.82
    osaurs
    0.77
    hetti
    0.76
     nostalg
    0.76
    hower
    0.74
     Frieza
    0.72
    Act Density 0.023%

    No Known Activations