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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets

    oai_token-act-pair · gpt-3.5-turbo

    constructs related to programming or coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cli
    -0.63
    ensis
    -0.60
    lease
    -0.60
     hem
    -0.57
     ferment
    -0.56
    hement
    -0.55
    mates
    -0.55
    omore
    -0.54
     oceans
    -0.54
     thor
    -0.54
    POSITIVE LOGITS
     Majesty
    0.79
     Honour
    0.69
    Tube
    0.68
     Uniform
    0.67
     Execution
    0.67
    Va
    0.66
     Bok
    0.66
    Zero
    0.63
     Own
    0.63
     Awakens
    0.62
    Act Density 1.346%

    No Known Activations