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

    Neuronpedia

    INDEX
    Explanations

    comparisons using the word "than"

    oai_token-act-pair · gpt-3.5-turbo

    comparisons that convey a sense of inadequacy or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.80
    leneck
    -0.72
    ibal
    -0.70
    edia
    -0.69
    alter
    -0.67
    ModLoader
    -0.67
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.64
    olith
    -0.62
    ilon
    -0.61
    ---------
    -0.61
    POSITIVE LOGITS
     SPORTS
    0.73
    anke
    0.67
    qqa
    0.66
     Jav
    0.64
     Pik
    0.63
     Fishing
    0.58
     practicable
    0.58
     Thieves
    0.57
    catch
    0.56
    DERR
    0.55
    Act Density 0.038%

    No Known Activations