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

    Neuronpedia

    INDEX
    Explanations

    references to historical periods and events, particularly wars and specific eras

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ancient
    -0.21
     Ancient
    -0.20
    anc
    -0.18
     Victorian
    -0.17
     apartheid
    -0.17
     Medieval
    -0.17
    andas
    -0.16
     older
    -0.16
    Anc
    -0.16
     дÑĢев
    -0.16
    POSITIVE LOGITS
    -era
    0.57
     era
    0.46
     Era
    0.43
    era
    0.40
    -period
    0.36
     period
    0.30
    /post
    0.27
    ERA
    0.27
    period
    0.26
    -times
    0.26
    Act Density 0.086%

    No Known Activations