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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the quality of things

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions and human experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "))
    -0.82
     Regarding
    -0.79
     Whilst
    -0.78
     [/
    -0.78
     Overall
    -0.74
    Currently
    -0.73
    "}
    -0.73
    Overall
    -0.73
    Due
    -0.73
    tains
    -0.73
    POSITIVE LOGITS
     exhilar
    0.83
     thrill
    0.80
     triumph
    0.78
     roar
    0.78
     shrug
    0.77
     gle
    0.74
     humili
    0.72
     consolation
    0.71
     demoral
    0.69
     plaint
    0.69
    Act Density 1.071%

    No Known Activations