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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a positive or negative attitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueGeneration
    -0.68
     BorderRadius
    -0.62
    Архівовано
    -0.60
    tvguidetime
    -0.59
     bezeichneter
    -0.57
     precisione
    -0.56
    DoubleQuotes
    -0.56
     McIl
    -0.56
    TestingModule
    -0.56
    providedIn
    -0.54
    POSITIVE LOGITS
     attitude
    0.91
     Attitude
    0.87
    attitude
    0.86
    DEFAULT
    0.81
    Attitude
    0.75
     Chwiliwch
    0.73
     ECONOMICS
    0.68
    economics
    0.68
     testified
    0.65
    Economics
    0.65
    Act Density 0.133%

    No Known Activations