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

    Neuronpedia

    INDEX
    Explanations

    numerical values as part of phrases

    oai_token-act-pair · gpt-3.5-turbo

    the word "Much" and phrases indicating quantity or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.72
    ħĭ
    -0.72
    pta
    -0.63
    slot
    -0.62
    oway
    -0.62
    opers
    -0.60
    pherd
    -0.60
    mediate
    -0.60
    ensis
    -0.59
    uble
    -0.59
    POSITIVE LOGITS
     happens
    1.22
     depends
    1.22
     happened
    1.07
     hinges
    0.99
     transpired
    0.97
     goes
    0.92
     depended
    0.91
     occurs
    0.90
     has
    0.83
     ensued
    0.81
    Act Density 0.087%

    No Known Activations