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

    Neuronpedia

    INDEX
    Explanations

    various qualities and functions of work-related scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Delay
    -0.15
    .Delay
    -0.15
    Delay
    -0.14
    niž
    -0.14
     Sunder
    -0.14
     lô
    -0.14
    _delay
    -0.14
    延
    -0.14
    /goto
    -0.13
    lined
    -0.13
    POSITIVE LOGITS
     subsequent
    0.21
     afterwards
    0.21
     thereafter
    0.20
    æļ®
    0.18
     ending
    0.18
     later
    0.17
     subsequently
    0.17
     finale
    0.17
     posterior
    0.17
     Ending
    0.17
    Act Density 0.367%

    No Known Activations