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

    Neuronpedia

    INDEX
    Explanations

    words related to positive interactions and supportive communities

    oai_token-act-pair · gpt-3.5-turbo

    negative consequences and issues related to systemic problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilet
    -0.74
    é¾
    -0.74
    cffffcc
    -0.68
    ãĤ´ãĥ³
    -0.68
    iland
    -0.67
    ilaterally
    -0.64
    MpServer
    -0.63
    REL
    -0.63
    vernight
    -0.62
    dry
    -0.61
    POSITIVE LOGITS
     afforded
    0.97
     they
    0.95
     wrought
    0.88
     bestowed
    0.82
     he
    0.78
     we
    0.78
     she
    0.78
     inherent
    0.74
     emanating
    0.73
     generated
    0.73
    Act Density 0.484%

    No Known Activations