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

    Neuronpedia

    INDEX
    Explanations

    questions or statements with uncertain or subjective implications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    joining
    -0.71
    Notable
    -0.69
    spir
    -0.65
     gamma
    -0.65
    padding
    -0.61
    anim
    -0.59
    owship
    -0.59
    cele
    -0.59
    mark
    -0.58
    knit
    -0.58
    POSITIVE LOGITS
    Answer
    1.71
     Answer
    1.51
     answer
    1.42
    swers
    1.27
     answers
    1.25
     answered
    1.20
    answer
    1.10
     reply
    0.97
     Nope
    0.96
     answ
    0.94
    Act Density 0.314%

    No Known Activations