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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss conditions or situations specifically regarding people and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.92
     and
    -0.52
     staden
    -0.48
     parcheggio
    -0.47
     africains
    -0.46
     térmica
    -0.45
     femininas
    -0.44
     combattre
    -0.43
     pernas
    -0.43
     Syrie
    -0.43
    POSITIVE LOGITS
     שוליים
    1.13
     nahilalakip
    1.04
    PerformLayout
    0.99
     Paglinawan
    0.96
    WithIOException
    0.95
    ThroughAttribute
    0.95
    NameInMap
    0.94
    ScopeManager
    0.94
    GEBURTSDATUM
    0.94
    tagext
    0.92
    Act Density 1.010%

    No Known Activations