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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to different versions or stages of a product or process

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "iteration" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entit
    -0.76
     certificates
    -0.73
    BN
    -0.71
    estine
    -0.70
     Book
    -0.69
     deaf
    -0.68
    nai
    -0.66
    shed
    -0.65
     Dept
    -0.65
     BOOK
    -0.65
    POSITIVE LOGITS
     iteration
    3.01
     iterations
    2.74
     tweak
    2.10
     iter
    2.06
     tweaking
    1.90
     tweaks
    1.85
    Iter
    1.80
     tweaked
    1.73
     tink
    1.68
     Iter
    1.65
    Act Density 0.035%

    No Known Activations