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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditions or specifications for processes or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.90
    Autoritní
    -0.89
     Paglinawan
    -0.85
     boî
    -0.83
    /**
    -0.81
     auroit
    -0.81
     démocr
    -0.76
     wikipagina
    -0.75
     Roskov
    -0.75
     vectorstock
    -0.75
    POSITIVE LOGITS
    ,
    0.71
     in
    0.70
    omitempty
    0.68
     as
    0.61
    </h2>
    0.59
     has
    0.59
     again
    0.58
     for
    0.58
     ajoutez
    0.58
    .
    0.58
    Act Density 0.187%

    No Known Activations