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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to intelligence and personal feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.83
     stanovnika
    -0.80
     snippetHide
    -0.78
    出版年
    -0.77
     становника
    -0.70
    WithIOException
    -0.68
    styleUrls
    -0.67
    ]-->
    -0.66
    OGND
    -0.66
    }}/>
    -0.64
    POSITIVE LOGITS
     hideous
    0.56
     kre
    0.55
     evil
    0.53
     shenanigans
    0.53
     glorious
    0.52
     mayhem
    0.51
     wretched
    0.51
     hapless
    0.51
     hij
    0.51
    {{{
    0.51
    Act Density 1.512%

    No Known Activations