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

    Neuronpedia

    INDEX
    Explanations

    words related to making changes or modifications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ublic
    -0.77
    çĦ
    -0.77
    GV
    -0.72
    glas
    -0.70
    gart
    -0.68
    acht
    -0.68
    gets
    -0.66
    fighter
    -0.65
    restling
    -0.65
    İ
    -0.64
    POSITIVE LOGITS
     parameters
    0.94
     behaviour
    0.90
     settings
    0.88
     aspects
    0.84
     existing
    0.84
     perceptions
    0.83
    ibly
    0.82
     configurations
    0.81
     wording
    0.81
     layouts
    0.79
    Act Density 0.136%

    No Known Activations