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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating encouragement or motivation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritional
    -0.82
    piracy
    -0.72
    chuk
    -0.72
    olesterol
    -0.72
    phrine
    -0.72
    iership
    -0.71
    INGTON
    -0.71
    «ĺ
    -0.69
    rongh
    -0.69
    ioxid
    -0.67
    POSITIVE LOGITS
    EMS
    0.64
     Salon
    0.62
     Clyde
    0.60
    places
    0.58
     Dres
    0.58
    URE
    0.58
    STEM
    0.58
     teeth
    0.57
     Dragonbound
    0.56
    Settings
    0.56
    Act Density 0.000%

    No Known Activations