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

    Neuronpedia

    INDEX
    Explanations

    legal case citations

    oai_token-act-pair · gpt-3.5-turbo

    legal case citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arrang
    -0.74
    tymology
    -0.73
    iott
    -0.72
     msec
    -0.69
     glim
    -0.69
    ,—
    -0.69
     shorthand
    -0.67
    .<
    -0.67
    ranch
    -0.67
     hence
    -0.67
    POSITIVE LOGITS
     TBD
    0.89
     CLS
    0.89
     Machine
    0.83
     Commissioner
    0.83
     Clash
    0.83
     Majority
    0.79
     Predator
    0.78
     Dep
    0.78
     Crew
    0.75
     Commonwealth
    0.73
    Act Density 0.033%

    No Known Activations