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

    Neuronpedia

    INDEX
    Explanations

    specific structural or format elements in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -1.53
     (
    -1.45
    ,
    -1.35
     "
    -1.31
     a
    -1.21
    /
    -1.20
    :
    -1.19
     I
    -1.18
     “
    -1.16
     in
    -1.16
    POSITIVE LOGITS
     itſelf
    1.83
     ་་
    1.82
     pleaſure
    1.62
     doubtnut
    1.60
     Houſe
    1.58
     ſind
    1.57
    ſelves
    1.56
     houſe
    1.55
     photolibrary
    1.55
     ―――――
    1.54
    Act Density 10.479%

    No Known Activations