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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles or research publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isse
    -0.16
    omet
    -0.15
     Lawson
    -0.15
     diffuse
    -0.14
    Ĥ¹
    -0.14
     nonetheless
    -0.14
     Briggs
    -0.14
     Sv
    -0.13
    ás
    -0.13
     CV
    -0.13
    POSITIVE LOGITS
    ERO
    0.16
    odem
    0.16
    ief
    0.16
     treff
    0.15
    efa
    0.15
     Yug
    0.14
    burger
    0.14
    ENCH
    0.14
    oled
    0.14
    oller
    0.14
    Act Density 0.003%

    No Known Activations