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

    Neuronpedia

    INDEX
    Explanations

    phrases related to visual observation or examination

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the verb "look" and its derivatives in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONCLUS
    -0.75
    è¦ļéĨĴ
    -0.71
    Fact
    -0.70
    accompan
    -0.67
    ãĥĩãĤ£
    -0.67
     Ans
    -0.66
     Recomm
    -0.66
    ãĥ´
    -0.65
     Trad
    -0.64
    LOD
    -0.63
    POSITIVE LOGITS
     disgusted
    1.04
     bored
    1.00
     pissed
    0.98
     horrified
    0.97
     distraught
    0.97
     puzzled
    0.96
     miserable
    0.92
     annoyed
    0.92
     tired
    0.92
     embarrassed
    0.92
    Act Density 0.052%

    No Known Activations