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

    Neuronpedia

    INDEX
    Explanations

    specific company names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cano
    -1.08
     Oro
    -0.88
    CENT
    -0.87
    icio
    -0.86
     Cyborg
    -0.84
     negotiator
    -0.82
     Andreas
    -0.81
     welf
    -0.81
     Tune
    -0.79
    cens
    -0.78
    POSITIVE LOGITS
    abies
    1.40
    igans
    1.34
    ãĤ¦ãĤ¹
    1.22
    igan
    1.19
    ollen
    1.17
    ãĥĥãĥī
    1.08
    isse
    1.08
    mouth
    1.04
    glers
    1.02
    lore
    1.02
    Act Density 2.322%

    No Known Activations