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

    Neuronpedia

    INDEX
    Explanations

    phrases related to precise methods or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     started
    -0.19
     start
    -0.19
     using
    -0.18
     use
    -0.18
     done
    -0.17
     put
    -0.16
     created
    -0.16
     needed
    -0.16
     used
    -0.16
    çĶ¨
    -0.16
    POSITIVE LOGITS
     occasion
    0.17
    occasion
    0.16
     rodin
    0.15
     bý
    0.15
    æķ·
    0.15
    renders
    0.14
    posit
    0.14
    коз
    0.14
    ourcem
    0.14
    arken
    0.14
    Act Density 0.031%

    No Known Activations