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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that suggest evaluation or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enige
    -0.66
    囗
    -0.54
    клопе
    -0.53
    存于互联网档案馆
    -0.51
    Diwedd
    -0.50
    ांकि
    -0.50
    esModule
    -0.49
    harusnya
    -0.49
     suivants
    -0.48
    ähkö
    -0.48
    POSITIVE LOGITS
     just
    4.19
    just
    3.59
    Just
    3.06
     Just
    2.97
     JUST
    2.68
     juste
    2.67
    JUST
    2.50
     juſt
    2.10
     juft
    2.07
     simply
    1.92
    Act Density 0.919%

    No Known Activations