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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating context or existence that occur outside a specified location or boundary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĢ¬
    -0.17
    AMY
    -0.15
    ots
    -0.15
    erus
    -0.14
    ark
    -0.14
    ì°©
    -0.14
    tron
    -0.14
    stones
    -0.14
    imat
    -0.14
    sets
    -0.14
    POSITIVE LOGITS
     usual
    0.23
     bounds
    0.21
     of
    0.20
    halb
    0.20
     traditional
    0.19
     obvious
    0.19
    à¹Ģหà¸Ļ
    0.19
     strictly
    0.19
     outside
    0.18
     normal
    0.17
    Act Density 0.028%

    No Known Activations