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

    Neuronpedia

    INDEX
    Explanations

    phrases related to giving opinions or analysis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "commentary" and its context throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riages
    -0.74
    bis
    -0.71
    chen
    -0.68
    wikipedia
    -0.67
    rir
    -0.66
    fw
    -0.65
    chrom
    -0.65
    bie
    -0.65
    ookie
    -0.64
    vet
    -0.63
    POSITIVE LOGITS
     commentary
    1.00
    jad
    0.81
     commentator
    0.69
    raint
    0.68
    isf
    0.67
     concerning
    0.67
     cartoons
    0.65
     analys
    0.64
    spection
    0.64
    mund
    0.63
    Act Density 0.035%

    No Known Activations