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

    Neuronpedia

    INDEX
    Explanations

    pieces of advice and tips related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieri
    -0.17
     nar
    -0.15
    wan
    -0.15
    _boot
    -0.14
    issy
    -0.14
    æīĺ
    -0.14
    TRACE
    -0.14
    ullen
    -0.14
    elsing
    -0.13
    èĪ
    -0.13
    POSITIVE LOGITS
    #
    0.20
    "Don
    0.19
     pay
    0.17
    don
    0.17
    pay
    0.17
     avoid
    0.16
    /Internal
    0.16
    Accessor
    0.16
     Always
    0.16
     Never
    0.16
    Act Density 0.313%

    No Known Activations