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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating someone excels or is proficient at a particular activity

    oai_token-act-pair · gpt-3.5-turbo

    repeated usage of the phrase "seems to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bats
    -0.72
     Rapids
    -0.68
    opens
    -0.67
    earable
    -0.67
     helicop
    -0.66
    aroo
    -0.63
    rella
    -0.62
    estern
    -0.62
    river
    -0.61
    ascript
    -0.61
    POSITIVE LOGITS
     indicate
    0.95
     embody
    0.91
     imply
    0.86
     differentiate
    0.85
     be
    0.85
     satisfy
    0.84
     settle
    0.84
     contradict
    0.83
     distinguish
    0.83
     derive
    0.81
    Act Density 0.065%

    No Known Activations