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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exitRule
    -0.56
    PRWEB
    -0.54
    ształ
    -0.53
     Flamen
    -0.50
    .*")]
    -0.50
     consultato
    -0.50
     Brecht
    -0.48
    Directive
    -0.48
     forgiving
    -0.47
    policies
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.66
     autorytatywna
    0.66
    PMailer
    0.63
    AddTagHelper
    0.59
    ValueGeneration
    0.55
    hells
    0.51
     Unlocked
    0.51
    ReusableCell
    0.51
     lenker
    0.51
    ⓧ
    0.50
    Act Density 0.280%

    No Known Activations