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

    Neuronpedia

    INDEX
    Explanations

    phrases related to radiation or similar contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to radiation and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OOL
    -0.78
    batch
    -0.75
    awaru
    -0.72
    stall
    -0.72
     Rowling
    -0.70
    folios
    -0.68
    erguson
    -0.67
    binding
    -0.67
    avanaugh
    -0.66
    eers
    -0.65
    POSITIVE LOGITS
     rad
    1.35
    iated
    1.18
    iation
    1.00
    iating
    0.98
    iance
    0.96
    iations
    0.95
    irtual
    0.93
    iate
    0.88
    ionics
    0.88
    ient
    0.85
    Act Density 0.003%

    No Known Activations