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

    Neuronpedia

    INDEX
    Explanations

    company acronyms preceded by numerical values, followed by descriptions or contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "NR"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beans
    -0.79
     bean
    -0.75
     Flav
    -0.72
    zza
    -0.71
     Sandwich
    -0.69
     Kou
    -0.68
     crucifix
    -0.67
    bean
    -0.67
     pies
    -0.65
     con
    -0.64
    POSITIVE LOGITS
    NR
    4.30
     NR
    2.90
    nr
    1.50
    LR
    1.30
    NL
    1.30
    NH
    1.29
    NP
    1.23
    NF
    1.22
    RN
    1.22
    NM
    1.21
    Act Density 0.020%

    No Known Activations