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

    Neuronpedia

    INDEX
    Explanations

    programming structures and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Trent
    -0.15
    levator
    -0.14
    ừa
    -0.14
     Äijỡ
    -0.14
    leen
    -0.14
    bole
    -0.14
     Soul
    -0.13
    unday
    -0.13
    lingen
    -0.13
     North
    -0.13
    POSITIVE LOGITS
    andra
    0.16
    tti
    0.14
    dorf
    0.14
    igu
    0.14
    صب
    0.14
    jeme
    0.14
    751
    0.14
    owitz
    0.14
    irst
    0.14
    ka
    0.14
    Act Density 0.025%

    No Known Activations