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

    Neuronpedia

    INDEX
    Explanations

    terms related to metaphor

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "metaphor" and various forms related to metaphorical language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignt
    -0.77
    oway
    -0.71
     tradem
    -0.71
     Citiz
    -0.70
    reditary
    -0.69
    emetery
    -0.68
    packing
    -0.67
    vals
    -0.66
     thorough
    -0.65
    bred
    -0.65
    POSITIVE LOGITS
     metaphor
    0.92
     metaphors
    0.85
    ically
    0.76
     analogy
    0.75
    aph
    0.71
     Interpret
    0.71
     hypot
    0.70
     wink
    0.68
     underpin
    0.65
     drown
    0.65
    Act Density 0.018%

    No Known Activations