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

    Neuronpedia

    INDEX
    Explanations

    French words or terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to alternative and artistic themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udder
    -0.81
    ORED
    -0.80
    ORE
    -0.80
    ãĥĥãĤ¯
    -0.77
    restrial
    -0.74
    arijuana
    -0.74
    Redd
    -0.73
    abies
    -0.71
    avorable
    -0.71
    OWS
    -0.71
    POSITIVE LOGITS
     Ãł
    1.09
     jour
    1.09
     la
    1.03
     propos
    0.97
     au
    0.90
     qui
    0.82
     faire
    0.80
    ¯¯¯¯
    0.80
     simultane
    0.79
    ï
    0.78
    Act Density 0.014%

    No Known Activations