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

    Neuronpedia

    INDEX
    Explanations

    dialogue interactions involving multiple characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    itational
    -0.77
    arcity
    -0.70
    Forge
    -0.68
    iffe
    -0.66
    ourse
    -0.64
    requently
    -0.64
    irie
    -0.64
    qus
    -0.63
    reated
    -0.62
    ourses
    -0.62
    POSITIVE LOGITS
     huh
    1.66
     eh
    1.48
     haha
    1.34
     sir
    1.28
     yeah
    1.09
     tho
    0.95
     lol
    0.95
     anyways
    0.93
     though
    0.91
     alright
    0.89
    Act Density 0.270%

    No Known Activations