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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software configuration and development

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "This" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aws
    -0.73
    Ĭ±
    -0.71
    gress
    -0.68
    ich
    -0.67
    lev
    -0.66
    ometown
    -0.65
    erity
    -0.65
    IDES
    -0.64
    izens
    -0.62
     Izan
    -0.62
    POSITIVE LOGITS
     corresponds
    1.09
     ensures
    1.07
     occurs
    1.05
     enables
    1.02
     allows
    1.01
     happens
    1.01
     differs
    1.00
     translates
    1.00
     prevents
    0.99
     excludes
    0.99
    Act Density 0.219%

    No Known Activations