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

    Neuronpedia

    INDEX
    Explanations

    references to a specific type of writing tool

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndum
    -0.73
    cffffcc
    -0.69
    ADS
    -0.65
    CVE
    -0.63
     Lanka
    -0.62
    debian
    -0.62
    âķIJâķIJ
    -0.62
     Zak
    -0.60
    ierrez
    -0.59
    rals
    -0.59
    POSITIVE LOGITS
    jet
    1.09
     cartridges
    1.02
     ink
    0.99
    prints
    0.99
    manship
    0.96
    lings
    0.95
    sworth
    0.94
     cartridge
    0.89
    bowl
    0.89
    clip
    0.88
    Act Density 0.021%

    No Known Activations