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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to computing and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     frequencies
    -0.80
     Explos
    -0.75
     Turk
    -0.74
    etheless
    -0.71
    ances
    -0.68
    entanyl
    -0.64
    abwe
    -0.64
    vor
    -0.63
    aila
    -0.62
    lov
    -0.62
    POSITIVE LOGITS
    Us
    0.75
    ICLE
    0.70
    IU
    0.67
    ZA
    0.63
    rational
    0.62
     capit
    0.62
    PB
    0.61
     [+
    0.61
     AAA
    0.59
    roma
    0.59
    Act Density 1.301%

    No Known Activations