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

    Neuronpedia

    INDEX
    Explanations

    words related to software and computer programming

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various elements and activities within a community or society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Transparency
    -0.59
     Bridges
    -0.57
    OTOS
    -0.55
     Accountability
    -0.54
    itars
    -0.54
     Trou
    -0.53
     Aging
    -0.52
     Rac
    -0.52
     White
    -0.52
     Crimes
    -0.51
    POSITIVE LOGITS
    ishly
    0.80
    xual
    0.71
     extraord
    0.65
     versa
    0.60
    enary
    0.59
     clad
    0.57
     proverb
    0.57
     derby
    0.57
    berries
    0.57
     inducing
    0.55
    Act Density 0.452%

    No Known Activations