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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases ending in a full stop

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey strong statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tack
    -0.83
     haul
    -0.78
     quir
    -0.74
     disemb
    -0.72
     mascul
    -0.70
     defe
    -0.70
    ¥ŀ
    -0.70
     pse
    -0.69
     bom
    -0.69
     brist
    -0.68
    POSITIVE LOGITS
     Lastly
    1.73
     Additionally
    1.71
     Furthermore
    1.66
     Needless
    1.61
     Therefore
    1.60
     Interestingly
    1.59
     Unfortunately
    1.59
     Regardless
    1.59
     However
    1.58
     Thankfully
    1.56
    Act Density 0.524%

    No Known Activations