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

    Neuronpedia

    INDEX
    Explanations

    references to future implications and considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endency
    -0.18
    ec
    -0.16
    ile
    -0.16
    egment
    -0.16
    uns
    -0.16
    ubble
    -0.16
    incer
    -0.15
    annel
    -0.15
    ampions
    -0.15
    rect
    -0.15
    POSITIVE LOGITS
    AMIL
    0.22
    ELLOW
    0.22
    LOOR
    0.21
    RACT
    0.21
    ERENCE
    0.20
    URN
    0.20
    ILING
    0.20
    UTURE
    0.20
    LOOD
    0.20
    UND
    0.19
    Act Density 0.011%

    No Known Activations