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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with professional certifications and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivent
    -0.17
    kop
    -0.15
    eÅŁ
    -0.15
    redicate
    -0.15
    åİ
    -0.14
     Wich
    -0.14
     Choi
    -0.14
    anni
    -0.14
    bers
    -0.14
    ooter
    -0.13
    POSITIVE LOGITS
    hte
    0.15
     pokoj
    0.15
    lub
    0.15
    .apply
    0.15
    apply
    0.14
    336
    0.14
    æīķ
    0.14
    eno
    0.14
     Glas
    0.13
    enze
    0.13
    Act Density 0.453%

    No Known Activations