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

    Neuronpedia

    INDEX
    Explanations

    words related to negative attributes or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "ugliness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.95
    ingham
    -0.93
    aver
    -0.90
    idential
    -0.89
    owder
    -0.86
    akings
    -0.83
    uther
    -0.82
    cedented
    -0.81
    OTA
    -0.79
    ortium
    -0.77
    POSITIVE LOGITS
     ugly
    1.11
     adolesc
    0.83
     elephant
    0.80
     crap
    0.77
     beasts
    0.77
     spectacle
    0.76
     fallout
    0.75
     glare
    0.71
     fades
    0.71
     barb
    0.70
    Act Density 0.006%

    No Known Activations