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

    Neuronpedia

    INDEX
    Explanations

    words related to crafting and do-it-yourself activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to crafting and DIY activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Haram
    -0.77
    RESULTS
    -0.74
    ¥µ
    -0.72
     Eighth
    -0.72
     Incarn
    -0.70
     pedestrians
    -0.68
     Mortal
    -0.67
     ancestral
    -0.66
     Fifth
    -0.66
    âĹ¼
    -0.66
    POSITIVE LOGITS
     kit
    1.16
     pouch
    1.08
     attachment
    1.08
     cutter
    1.07
    cloth
    1.06
     adhesive
    1.05
     tray
    1.01
     adapter
    1.01
     tool
    1.00
     liner
    1.00
    Act Density 0.322%

    No Known Activations