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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critical statements or actions regarding societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    holes
    -0.73
    ordes
    -0.67
    adle
    -0.65
    keye
    -0.65
    oute
    -0.64
    arrass
    -0.64
    okers
    -0.64
    ertain
    -0.63
    aunders
    -0.61
    /#
    -0.61
    POSITIVE LOGITS
     week
    1.33
     month
    1.31
     year
    1.20
     night
    1.08
     summer
    1.01
     semester
    0.99
     weekend
    0.96
     decade
    0.95
     Month
    0.94
     autumn
    0.91
    Act Density 0.061%

    No Known Activations