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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    phrases where the speaker expresses personal thoughts or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assembly
    -0.74
    odder
    -0.69
    ife
    -0.68
    ume
    -0.68
    hello
    -0.67
     Farming
    -0.67
    ãĥīãĥ©
    -0.67
    uffs
    -0.65
     surg
    -0.65
    sheet
    -0.64
    POSITIVE LOGITS
    lycer
    0.73
     misunder
    0.70
     beh
    0.67
     faire
    0.67
     underest
    0.66
    stanbul
    0.65
     exagger
    0.64
     embr
    0.63
     underestimated
    0.63
     overest
    0.63
    Act Density 0.172%

    No Known Activations