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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contrasts between different subjects or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CAST
    -0.77
    ESA
    -0.71
    ipers
    -0.68
    ART
    -0.67
    aukee
    -0.66
    weather
    -0.66
    BAT
    -0.65
    illion
    -0.64
    anie
    -0.63
    $$
    -0.63
    POSITIVE LOGITS
     contrast
    1.15
     particular
    0.91
     whom
    0.85
     nutshell
    0.81
     turn
    0.78
     conjunction
    0.74
     contrad
    0.71
    whose
    0.69
     cooperation
    0.69
     whose
    0.68
    Act Density 0.071%

    No Known Activations