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

    Neuronpedia

    INDEX
    Explanations

    positive and negative adjectives

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that denote positive or negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steps
    -0.89
    ques
    -0.83
    busters
    -0.77
     Measures
    -0.76
    hops
    -0.76
    iddles
    -0.75
    ateurs
    -0.75
     breaches
    -0.74
    changes
    -0.74
    Nazis
    -0.74
    POSITIVE LOGITS
     knack
    1.30
     tendency
    1.29
     penchant
    1.28
     reputation
    1.23
     relationship
    1.10
     grasp
    1.09
     inclination
    1.03
     foothold
    1.03
     outlook
    1.03
     propensity
    1.03
    Act Density 0.272%

    No Known Activations