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

    Neuronpedia

    INDEX
    Explanations

    adjectives to express opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or judgments about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.81
    assembly
    -0.74
    andise
    -0.72
    è¦ļéĨĴ
    -0.67
    ield
    -0.66
    ulner
    -0.66
    ows
    -0.65
    alogue
    -0.65
    EE
    -0.65
    ife
    -0.64
    POSITIVE LOGITS
     misunder
    0.99
     beh
    0.75
     faire
    0.74
     misunderstood
    0.73
     somew
    0.73
     underest
    0.72
     deserved
    0.72
     underestimated
    0.71
     miscon
    0.71
     misconception
    0.70
    Act Density 0.260%

    No Known Activations