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

    Neuronpedia

    INDEX
    Explanations

    sentences related to criticism or negative assessment

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encount
    -0.84
    iosyncr
    -0.83
    ozyg
    -0.82
     quir
    -0.82
     satell
    -0.82
     carbohyd
    -0.81
     concess
    -0.80
     directional
    -0.79
    ¥ŀ
    -0.79
     synthes
    -0.78
    POSITIVE LOGITS
     Shame
    1.67
     Worse
    1.64
     Surely
    1.33
     Instead
    1.31
     Why
    1.25
     Seriously
    1.25
    Instead
    1.22
     Furthermore
    1.21
     Thankfully
    1.20
     Wouldn
    1.19
    Act Density 0.503%

    No Known Activations