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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific entities or things of notable interest

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pigs
    -0.71
    /,
    -0.64
     whilst
    -0.63
    ixel
    -0.62
    cellence
    -0.61
    zac
    -0.59
     haha
    -0.58
    )",
    -0.58
    Í
    -0.57
    cise
    -0.56
    POSITIVE LOGITS
     reverted
    0.78
     prevailed
    0.71
     vanished
    0.69
     seemed
    0.68
     remains
    0.67
     fared
    0.64
     succeeded
    0.64
     appears
    0.63
     underwent
    0.62
     remained
    0.62
    Act Density 1.143%

    No Known Activations