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

    Neuronpedia

    INDEX
    Explanations

    terms related to additions or extra elements to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to quantity or a statistical measure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LAN
    -0.92
    rog
    -0.78
    adr
    -0.71
    got
    -0.70
    aby
    -0.70
    rius
    -0.69
    wolf
    -0.69
    athe
    -0.68
     Turing
    -0.67
    bull
    -0.67
    POSITIVE LOGITS
     acres
    0.80
     sized
    0.80
     ILCS
    0.78
     minutes
    0.73
     pounds
    0.72
     degrees
    0.71
     pages
    0.70
     breaths
    0.69
     years
    0.68
     hours
    0.65
    Act Density 0.019%

    No Known Activations