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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate steps in a process or comparative assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoe
    -0.16
     Diy
    -0.15
    uç
    -0.14
    uat
    -0.14
    ÅĻ
    -0.14
    _vlog
    -0.13
     Unsafe
    -0.13
    arkan
    -0.13
    blr
    -0.13
    abet
    -0.13
    POSITIVE LOGITS
     again
    0.17
     straightforward
    0.16
     least
    0.15
     interesting
    0.15
    /archive
    0.14
     Again
    0.14
     another
    0.14
     most
    0.14
     controversial
    0.14
    Again
    0.14
    Act Density 0.225%

    No Known Activations