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

    Neuronpedia

    INDEX
    Explanations

    terms related to construction or development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    andra
    -0.73
    izon
    -0.72
    ican
    -0.71
    my
    -0.71
    Published
    -0.67
    sweet
    -0.66
    mia
    -0.66
     Rollins
    -0.65
    dos
    -0.65
    kov
    -0.65
    POSITIVE LOGITS
     bridges
    0.92
     Bridges
    0.86
     scaff
    0.84
    ILD
    0.76
     blocks
    0.76
     Blocks
    0.76
     suspense
    0.75
    raper
    0.75
    built
    0.75
     prototypes
    0.75
    Act Density 0.570%

    No Known Activations