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

    Neuronpedia

    INDEX
    Explanations

    words related to ethical or moral involvement, such as 'complicit', 'complicity', 'knowingly', and 'acquiesced'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to involvement and accountability in unethical or illegal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aster
    -0.77
    aign
    -0.74
    anche
    -0.72
     Rapt
    -0.68
    oult
    -0.66
    gar
    -0.65
    eways
    -0.65
    grim
    -0.63
     Feld
    -0.62
     Krish
    -0.62
    POSITIVE LOGITS
     complicit
    1.18
     complicity
    1.02
    ãĥ¼ãĥĨãĤ£
    0.92
     wink
    0.80
    vous
    0.78
     acquies
    0.78
     unwitting
    0.78
    ãĤº
    0.78
     unknow
    0.77
    cence
    0.74
    Act Density 0.022%

    No Known Activations