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

    Neuronpedia

    INDEX
    Explanations

    quantifiers denoting a large or notable quantity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quantity and existence within a group or population

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     syndrome
    -0.66
    air
    -0.61
    ight
    -0.61
    fuck
    -0.60
    orde
    -0.60
    itivity
    -0.59
    doesn
    -0.58
     Think
    -0.58
    noon
    -0.57
    ority
    -0.57
    POSITIVE LOGITS
     notably
    0.74
    accompanied
    0.71
     resembling
    0.70
     prominently
    0.69
     belonging
    0.69
     totaling
    0.68
     preferring
    0.66
     consisting
    0.66
     accompanied
    0.65
     intending
    0.65
    Act Density 0.143%

    No Known Activations