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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of inclusion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inclusion and exclusion in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decl
    -0.69
    acca
    -0.69
    CLASSIFIED
    -0.67
     Indust
    -0.63
    ELL
    -0.63
    ETS
    -0.62
    ¯¯¯¯¯¯¯¯
    -0.61
    ectar
    -0.61
     rpm
    -0.60
     bath
    -0.59
    POSITIVE LOGITS
    xual
    0.88
    ary
    0.81
    clusion
    0.80
     criteria
    0.79
    ibility
    0.79
    tions
    0.78
    ively
    0.78
    obyl
    0.77
    ivist
    0.74
    alist
    0.71
    Act Density 0.022%

    No Known Activations