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

    Neuronpedia

    INDEX
    Explanations

    words ending in '-ending' or '-ending' itself

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     mole
    -0.65
    姫
    -0.64
     ox
    -0.63
     Britann
    -0.62
     LAR
    -0.61
     phot
    -0.61
     kit
    -0.60
     synerg
    -0.60
     thermal
    -0.59
     album
    -0.59
    POSITIVE LOGITS
    ending
    4.30
    ends
    2.72
    ended
    2.71
    enders
    2.59
    END
    2.22
    ender
    2.17
    end
    2.08
    ENDED
    1.73
    ension
    1.48
    ensions
    1.30
    Act Density 0.011%

    No Known Activations