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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating locations or physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unami
    -0.18
    lero
    -0.17
     å®
    -0.15
    ite
    -0.15
    veloper
    -0.15
     Dale
    -0.15
    rts
    -0.14
    fir
    -0.14
    (strpos
    -0.14
    rish
    -0.14
    POSITIVE LOGITS
    ovacÃŃ
    0.16
    맹
    0.15
    haar
    0.14
    altar
    0.14
     Rag
    0.14
    ensch
    0.14
     bow
    0.14
     wet
    0.14
    lesen
    0.14
    iÄĩ
    0.13
    Act Density 0.645%

    No Known Activations