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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals, especially professionals or experts in their fields

    oai_token-act-pair · gpt-3.5-turbo

    statements made by authorities or experts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clubhouse
    -0.76
    tumblr
    -0.73
     canoe
    -0.69
     manifesto
    -0.60
     tune
    -0.59
     robbers
    -0.58
     conquering
    -0.57
     yacht
    -0.57
     partying
    -0.57
     deduction
    -0.57
    POSITIVE LOGITS
    ovich
    0.97
    ansky
    0.88
    inski
    0.87
     (@
    0.85
    mann
    0.84
    auer
    0.84
    enberg
    0.79
    uria
    0.79
    gaard
    0.78
    inger
    0.78
    Act Density 0.562%

    No Known Activations