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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism and evaluation of various topics

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and structured lists within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.57
     challeng
    -0.56
     disadvant
    -0.56
    chnology
    -0.53
    abase
    -0.52
     corrid
    -0.51
    coni
    -0.51
    VERTISEMENT
    -0.50
    arde
    -0.48
     helicop
    -0.48
    POSITIVE LOGITS
     please
    0.83
    please
    0.73
     huh
    0.70
     albeit
    0.63
     thank
    0.59
     PLEASE
    0.59
     sir
    0.58
     yeah
    0.58
     though
    0.58
     uh
    0.58
    Act Density 0.372%

    No Known Activations