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

    Neuronpedia

    INDEX
    Explanations

    words related to intense criticism or negative judgment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iture
    -0.73
    ties
    -0.71
    mast
    -0.69
    ebin
    -0.67
    iem
    -0.66
    sburgh
    -0.64
     Farmers
    -0.64
    formation
    -0.64
    oral
    -0.64
    fman
    -0.63
    POSITIVE LOGITS
     underrated
    0.81
     ambitious
    0.80
     optimistic
    0.76
     appealing
    0.76
     expanding
    0.76
     inventive
    0.75
     impractical
    0.75
     popular
    0.75
     entertaining
    0.75
     profitable
    0.74
    Act Density 0.048%

    No Known Activations