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

    Neuronpedia

    INDEX
    Explanations

    untested or unverified information or claims

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    anwhile
    -0.88
    姫
    -0.76
    hyde
    -0.73
    phrine
    -0.72
    SHIP
    -0.71
     Pigs
    -0.67
     briefs
    -0.67
    cium
    -0.66
    ŃĶ
    -0.66
    */(
    -0.65
    POSITIVE LOGITS
    ruly
    1.11
    itled
    1.05
    ested
    0.97
    rave
    0.96
    ribut
    0.94
    enable
    0.94
    ired
    0.92
    ainted
    0.92
    race
    0.89
    oward
    0.89
    Act Density 6.698%

    No Known Activations