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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the action of representing or describing something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the act of portrayal and how characters or subjects are represented or depicted

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ni
    -0.71
    sterdam
    -0.67
    iqueness
    -0.66
    foreseen
    -0.63
     confir
    -0.62
    iasm
    -0.61
    andr
    -0.61
    imil
    -0.61
     Skydragon
    -0.61
    won
    -0.60
    POSITIVE LOGITS
     portray
    1.07
     depictions
    0.93
     portrayal
    0.90
    istically
    0.89
     portraying
    0.85
    ROR
    0.84
     portrays
    0.81
     vividly
    0.81
     images
    0.79
    ãĤ¨ãĥ«
    0.79
    Act Density 0.125%

    No Known Activations