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

    Neuronpedia

    INDEX
    Explanations

    similes comparing actions to physical force or intensity

    oai_token-act-pair · gpt-3.5-turbo

    similes and metaphors that employ the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VICE
    -0.82
    ulic
    -0.76
    inion
    -0.70
    inas
    -0.69
    icipated
    -0.68
    iets
    -0.67
     Together
    -0.67
    Enlarge
    -0.65
    SEE
    -0.65
    vantage
    -0.65
    POSITIVE LOGITS
     wildfire
    1.27
     crazy
    1.01
     clock
    0.93
    liest
    0.91
     mad
    0.89
    lier
    0.89
     bandits
    0.87
     rabbits
    0.82
     mushrooms
    0.82
     never
    0.81
    Act Density 0.069%

    No Known Activations