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

    Neuronpedia

    INDEX
    Explanations

    references to personal transformation and the need for acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egend
    -0.15
    uish
    -0.15
    .Clamp
    -0.15
    $MESS
    -0.14
    iang
    -0.14
    arel
    -0.14
    _HOUR
    -0.14
    åľ°ä¸ĭ
    -0.14
     Rehab
    -0.14
    aryl
    -0.13
    POSITIVE LOGITS
     my
    0.18
    ijken
    0.16
     myself
    0.15
    577
    0.15
     Kund
    0.14
     collegiate
    0.14
     remin
    0.14
     c
    0.14
     cert
    0.14
    paque
    0.14
    Act Density 1.025%

    No Known Activations