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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a numerical quantity of additional items or time

    oai_token-act-pair · gpt-3.5-turbo

    references to an additional quantity or the concept of "more."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obar
    -0.78
    oes
    -0.78
    Gra
    -0.71
    both
    -0.69
    ISTER
    -0.69
    orig
    -0.68
    odor
    -0.68
    ĺħ
    -0.68
    ê
    -0.67
    Enlarge
    -0.67
    POSITIVE LOGITS
     than
    1.10
     ado
    0.93
     installments
    0.87
     stringent
    0.73
     elaborate
    0.73
    worldly
    0.70
     bedrooms
    0.69
     Than
    0.69
     rounds
    0.68
     mature
    0.68
    Act Density 0.073%

    No Known Activations