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

    Neuronpedia

    INDEX
    Explanations

    metaphorical descriptions using similes, where one object is likened to another

    oai_token-act-pair · gpt-3.5-turbo

    similes and metaphors that use vivid imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aido
    -0.71
     independents
    -0.66
    idates
    -0.64
    itutional
    -0.63
     concess
    -0.61
     Adin
    -0.61
     Survivors
    -0.60
    rity
    -0.59
     Violent
    -0.59
     Equality
    -0.59
    POSITIVE LOGITS
    mouse
    0.80
     sponge
    0.75
     unto
    0.73
    paste
    0.71
     iceberg
    0.70
     magnet
    0.70
    itaire
    0.68
     microscope
    0.68
     hier
    0.64
     hides
    0.63
    Act Density 0.357%

    No Known Activations