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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ide" or variations like "side" or "tide"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ideation or conceptualization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STON
    -0.65
    INESS
    -0.62
     "$:/
    -0.61
    é¾
    -0.60
    thening
    -0.60
    enegger
    -0.59
    %]
    -0.59
     Carbuncle
    -0.59
     Swordsman
    -0.57
    THING
    -0.56
    POSITIVE LOGITS
    ide
    1.18
    IDE
    0.98
    lli
    0.86
    IDES
    0.85
    verty
    0.85
    llo
    0.82
    ides
    0.82
    aux
    0.81
    ally
    0.79
    bike
    0.76
    Act Density 0.013%

    No Known Activations