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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tour"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tour."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iod
    -0.70
     STATE
    -0.61
     alloy
    -0.57
     Sr
    -0.57
    lesi
    -0.57
     Lub
    -0.56
     Pearce
    -0.56
     Kers
    -0.55
     brightest
    -0.54
     Saban
    -0.54
    POSITIVE LOGITS
    neys
    1.34
    ney
    1.25
    neau
    1.07
     itiner
    1.01
    icular
    1.00
    ogue
    0.92
     tour
    0.86
    mal
    0.86
    efully
    0.84
    ajo
    0.80
    Act Density 0.031%

    No Known Activations