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

    Neuronpedia

    INDEX
    Explanations

    specific details and indicators of reasoned arguments in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -1.19
     (
    -1.15
     "
    -1.09
    ,
    -1.08
    /
    -1.01
     a
    -0.99
     “
    -0.98
    :
    -0.98
     I
    -0.96
     in
    -0.94
    POSITIVE LOGITS
     ་་
    1.30
     itſelf
    1.13
     photolibrary
    1.10
     pleaſure
    1.04
     ainfi
    1.03
     doubtnut
    1.01
     ſind
    1.01
    ſelves
    1.01
     vectorstock
    1.00
     mauva
    0.98
    Act Density 10.801%

    No Known Activations