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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disagreement and political ideologies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    amina
    -0.62
    GV
    -0.57
    oufl
    -0.55
     Roads
    -0.54
    hens
    -0.54
     adrenaline
    -0.53
     Jackets
    -0.53
    maximum
    -0.52
    spring
    -0.51
    IFT
    -0.50
    POSITIVE LOGITS
    rences
    0.72
     vehemently
    0.69
    ially
    0.66
    uously
    0.63
    lihood
    0.63
    ably
    0.62
     disagree
    0.62
    atively
    0.61
     passionately
    0.60
    ively
    0.60
    Act Density 7.929%

    No Known Activations