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

    Neuronpedia

    INDEX
    Explanations

    distinctions and differences in concepts or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    477
    -0.16
    roz
    -0.15
     valueForKey
    -0.15
     Sle
    -0.14
    ognito
    -0.14
    zz
    -0.14
     gezocht
    -0.14
    pra
    -0.14
     sle
    -0.14
    posure
    -0.14
    POSITIVE LOGITS
    mere
    0.17
     mere
    0.15
    afil
    0.14
    /classes
    0.14
    enu
    0.14
    HZ
    0.14
    _collect
    0.13
     distinction
    0.13
     Goods
    0.13
    ìĹŃ
    0.13
    Act Density 0.096%

    No Known Activations