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

    Neuronpedia

    INDEX
    Explanations

    phrases related to narrative storytelling or instructional information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.90
    etheless
    -0.81
    patrick
    -0.65
    stress
    -0.64
     nevertheless
    -0.63
    pei
    -0.62
    inger
    -0.62
    esan
    -0.62
    rect
    -0.61
    cerpt
    -0.59
    POSITIVE LOGITS
     aesthetics
    0.61
     paycheck
    0.59
     pian
    0.57
    omical
    0.57
    ifiable
    0.57
     aest
    0.56
     fixme
    0.55
     guiActive
    0.55
     visually
    0.55
    DERR
    0.54
    Act Density 0.109%

    No Known Activations