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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations or people's names which include the string "li"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "li."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Psy
    -0.70
     psychedel
    -0.67
     converge
    -0.66
     spark
    -0.64
     Vortex
    -0.63
     Ubuntu
    -0.63
     CoC
    -0.62
     cutoff
    -0.61
     morph
    -0.60
     affinity
    -0.60
    POSITIVE LOGITS
    li
    4.42
     li
    1.79
    lie
    1.76
    lia
    1.73
    lies
    1.57
    la
    1.54
    lis
    1.52
    lio
    1.51
    Li
    1.47
    lo
    1.47
    Act Density 0.007%

    No Known Activations