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

    Neuronpedia

    INDEX
    Explanations

    text related to personal experiences and storytelling

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     stili
    -0.73
     iyon
    -0.72
     araw
    -0.71
     alfabe
    -0.66
     bago
    -0.66
     OMITTED
    -0.65
     Ouverture
    -0.65
     makro
    -0.64
    comuna
    -0.64
     Kategor
    -0.64
    POSITIVE LOGITS
     unspeak
    0.96
     Wtf
    0.92
     McLaugh
    0.87
     apprehen
    0.86
     Lmao
    0.83
     gaily
    0.82
     unlaw
    0.79
     Souha
    0.79
     shenan
    0.78
     friends
    0.78
    Act Density 0.199%

    No Known Activations