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

    Neuronpedia

    INDEX
    Explanations

    references to keyword "neutrality" in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.82
    universal
    -0.80
    depending
    -0.75
    itious
    -0.73
     oneself
    -0.73
    ealous
    -0.69
    idious
    -0.67
    soType
    -0.67
    yss
    -0.66
    inational
    -0.65
    POSITIVE LOGITS
     coordinator
    0.79
     Coordinator
    0.72
     Ambassador
    0.70
     Summit
    0.70
     cz
    0.69
     Expo
    0.68
     Ltd
    0.63
     Association
    0.62
     Conference
    0.61
     fame
    0.60
    Act Density 0.466%

    No Known Activations