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

    Neuronpedia

    INDEX
    Explanations

    references to specific volumes of academic or scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.11
    ^(@)
    -1.09
    DockStyle
    -1.02
     occaf
    -1.01
     photolibrary
    -1.01
    ValueStyle
    -1.00
     Efq
    -0.97
    wiſe
    -0.96
     cauſe
    -0.95
     raiſ
    -0.95
    POSITIVE LOGITS
    zu
    0.72
    RB
    0.61
     der
    0.59
    ↵↵
    0.58
    los
    0.58
    \
    0.58
    rb
    0.58
    level
    0.57
    old
    0.57
     
    0.55
    Act Density 0.111%

    No Known Activations