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

    Neuronpedia

    INDEX
    Explanations

    time-related words and expressions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.69
     corrid
    -0.68
     streng
    -0.64
     looph
    -0.64
    SourceFile
    -0.59
    clud
    -0.58
     endors
    -0.58
    igl
    -0.57
    afety
    -0.57
    dinand
    -0.56
    POSITIVE LOGITS
    Reviewer
    0.89
     where
    0.69
     attRot
    0.68
    isphere
    0.67
     ago
    0.67
     (~
    0.66
     respectively
    0.66
    rave
    0.65
    -[
    0.64
     when
    0.64
    Act Density 0.222%

    No Known Activations