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

    Neuronpedia

    INDEX
    Explanations

    greetings and well wishes

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain conclusions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.78
     compr
    -0.76
     magically
    -0.73
    itability
    -0.73
     bonded
    -0.70
    awaru
    -0.68
    opian
    -0.68
     subsequ
    -0.68
    ignty
    -0.67
     teasp
    -0.66
    POSITIVE LOGITS
     Examples
    1.55
     Firstly
    1.55
     Among
    1.54
     Including
    1.51
     Specifically
    1.46
     Notably
    1.43
     These
    1.38
     Included
    1.34
     Particularly
    1.29
     Some
    1.26
    Act Density 0.477%

    No Known Activations