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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating spatial or temporal relationships

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and conjunctions indicating relationships in time and place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.75
    dh
    -0.72
    aban
    -0.71
    ingen
    -0.68
    ienne
    -0.63
    DAQ
    -0.62
    anger
    -0.61
    obin
    -0.61
    essen
    -0.60
    IZE
    -0.59
    POSITIVE LOGITS
    ©¶æ
    0.76
     "{
    0.66
     majority
    0.64
    ĨĴ
    0.62
    jong
    0.61
     polled
    0.60
    esta
    0.57
     ));
    0.57
     Badge
    0.56
    Sphere
    0.55
    Act Density 0.177%

    No Known Activations