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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions of scenes or settings in video games

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    MENT
    -0.74
    VICE
    -0.73
    NAME
    -0.73
    ML
    -0.72
    TE
    -0.71
     Lawyers
    -0.71
     Guilty
    -0.69
     Shots
    -0.69
    oulos
    -0.69
    calling
    -0.68
    POSITIVE LOGITS
     decay
    0.98
     resh
    0.96
     conquer
    0.94
     rearr
    0.94
     evolve
    0.93
     folds
    0.93
     innovate
    0.93
     discontin
    0.92
     reorgan
    0.91
     simplify
    0.89
    Act Density 0.328%

    No Known Activations