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

    Neuronpedia

    INDEX
    Explanations

    keywords related to various programs or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emouth
    -0.84
    ioned
    -0.73
    afort
    -0.69
    ãĥķãĤ©
    -0.68
    auri
    -0.66
    beer
    -0.65
     Bale
    -0.65
    Ļ½
    -0.63
    soType
    -0.63
    inness
    -0.62
    POSITIVE LOGITS
     program
    3.59
     Program
    2.72
     programs
    2.67
     programme
    2.51
     Programs
    2.28
    program
    2.27
     PROGRAM
    2.14
    Program
    2.08
     programmes
    1.80
     Programme
    1.78
    Act Density 0.025%

    No Known Activations