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

    Neuronpedia

    INDEX
    Explanations

    short sequences of characters that form URLs or IP addresses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical data and quantifiable expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.89
    ahime
    -0.82
    avis
    -0.80
    aman
    -0.78
     Aus
    -0.77
    avia
    -0.76
    avid
    -0.74
    av
    -0.74
     consum
    -0.73
     Agric
    -0.73
    POSITIVE LOGITS
    rand
    0.82
     fri
    0.72
     lapt
    0.70
    lett
    0.70
    quickShipAvailable
    0.68
     finger
    0.68
    ksh
    0.67
    LET
    0.66
    ricks
    0.66
     fingert
    0.65
    Act Density 0.778%

    No Known Activations