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

    Neuronpedia

    INDEX
    Explanations

    special characters, specifically those resembling double lines like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of uncertainty or ambiguity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Droid
    -0.68
    oteric
    -0.63
     joints
    -0.63
    obar
    -0.63
     Patreon
    -0.62
     Druid
    -0.61
     Zup
    -0.59
     ACS
    -0.58
    ibrary
    -0.58
    antine
    -0.57
    POSITIVE LOGITS
    ]"
    0.84
    '"
    0.80
    Sport
    0.80
    "
    0.79
    However
    0.76
    Poll
    0.76
    )"
    0.75
    .,"
    0.74
    sports
    0.74
    Shape
    0.74
    Act Density 0.200%

    No Known Activations