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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community outreach and engagement efforts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Proced
    -0.70
    alogue
    -0.70
    icester
    -0.69
    osing
    -0.68
    aration
    -0.67
    peg
    -0.66
    abases
    -0.65
    士
    -0.65
    oreal
    -0.65
    hov
    -0.63
    POSITIVE LOGITS
     outreach
    0.81
    ourcing
    0.78
    orescence
    0.77
    sites
    0.77
    aukee
    0.76
    clinton
    0.75
    yip
    0.74
    guide
    0.68
    thank
    0.67
    lar
    0.66
    Act Density 5.866%

    No Known Activations