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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to making an argument or presenting a point

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ties
    -0.74
    sed
    -0.69
    vim
    -0.68
    walking
    -0.68
    pher
    -0.66
    bos
    -0.64
    dies
    -0.64
    sav
    -0.63
    nz
    -0.61
    retched
    -0.59
    POSITIVE LOGITS
     responders
    1.06
     impressions
    0.91
     baseman
    0.83
     Steps
    0.79
     glance
    0.76
     Respond
    0.73
     ancest
    0.71
     Corinthians
    0.70
     Published
    0.70
     Name
    0.69
    Act Density 0.041%

    No Known Activations