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

    Neuronpedia

    INDEX
    Explanations

    the verb "portray" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "portray" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duct
    -0.84
    foreseen
    -0.83
    sterdam
    -0.81
    wegian
    -0.74
    speak
    -0.71
    zyme
    -0.67
    raid
    -0.64
    foundation
    -0.63
    seq
    -0.61
    scrib
    -0.61
    POSITIVE LOGITS
     portray
    1.16
     portrays
    1.14
     depictions
    1.09
     portrayal
    1.04
    rities
    0.97
     portraying
    0.90
     depicts
    0.90
    ãĤ¨ãĥ«
    0.88
     depicting
    0.86
     depiction
    0.86
    Act Density 0.022%

    No Known Activations