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

    Neuronpedia

    INDEX
    Explanations

    comments or opinions expressed in a conversation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.64
     unsurprisingly
    -0.55
    ãĤº
    -0.55
     Hels
    -0.55
     Shutterstock
    -0.54
    ãĢij
    -0.54
     Recall
    -0.53
    Moreover
    -0.52
     Additionally
    -0.51
     Further
    -0.51
    POSITIVE LOGITS
    laughs
    0.94
     gonna
    0.94
     fuckin
    0.88
     wanna
    0.81
     gotta
    0.80
     kinda
    0.80
    Laughs
    0.78
     âĢ¦"
    0.78
     [
    0.77
     guys
    0.74
    Act Density 0.961%

    No Known Activations