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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to user interface elements and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.45
     publiek
    -0.41
     gekomen
    -0.40
    OrBuilder
    -0.39
     kræ
    -0.37
     gehad
    -0.37
    RTHOOK
    -0.36
     ontdek
    -0.36
    ništvo
    -0.36
     originais
    -0.36
    POSITIVE LOGITS
     tartalomajánló
    0.55
     dummy
    0.53
     purpoſe
    0.52
     contextLoads
    0.52
    AndEndTag
    0.51
    GEBURTSDATUM
    0.51
     intentionally
    0.50
     Dewi
    0.49
    dummy
    0.48
    хьтан
    0.47
    Act Density 0.591%

    No Known Activations