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

    Neuronpedia

    INDEX
    Explanations

    words signaling comparison or potential actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ety
    -0.78
    iple
    -0.69
    cember
    -0.65
    herent
    -0.62
    lore
    -0.61
    uscript
    -0.59
    usra
    -0.59
    lord
    -0.59
    vre
    -0.58
     nutshell
    -0.58
    POSITIVE LOGITS
     regardless
    1.21
     lest
    1.19
     preferably
    1.18
     irrespective
    1.08
     thereby
    1.04
     albeit
    1.03
     however
    0.98
     whereas
    0.93
     unless
    0.93
     depending
    0.93
    Act Density 0.584%

    No Known Activations