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

    Neuronpedia

    INDEX
    Explanations

    curse words

    oai_token-act-pair · gpt-3.5-turbo

    informal expressions of strong emotion or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     telecommunications
    -0.78
     intra
    -0.78
     Proceedings
    -0.77
     Directorate
    -0.75
     exclusion
    -0.74
     advisory
    -0.74
     Partnership
    -0.73
     susceptibility
    -0.73
     Transition
    -0.72
     Provision
    -0.71
    POSITIVE LOGITS
    aaaa
    1.08
    !!!
    1.07
    !!!!
    1.06
    !!!!!
    1.06
    eeee
    1.04
     haha
    1.03
     ;)
    1.03
    oooo
    1.03
    fuck
    1.02
    laughs
    1.01
    Act Density 0.679%

    No Known Activations