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

    Neuronpedia

    INDEX
    Explanations

    dialogue interactions between characters in a conversation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inement
    -0.75
     overl
    -0.70
     staged
    -0.66
    ilater
    -0.65
     pursu
    -0.64
     targeted
    -0.64
     transgress
    -0.63
     multiplied
    -0.63
     decorations
    -0.63
     reckoning
    -0.63
    POSITIVE LOGITS
     Yeah
    1.22
     Alright
    1.11
     Hmm
    1.02
     Hey
    0.98
     Exactly
    0.96
     Okay
    0.96
     Firstly
    0.96
     Hello
    0.94
    Yeah
    0.94
     Originally
    0.93
    Act Density 0.061%

    No Known Activations