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

    Neuronpedia

    INDEX
    Explanations

    references to mutual relationships or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sensei
    -0.68
     Serbs
    -0.62
    didSet
    -0.61
     DOJ
    -0.59
     Dems
    -0.59
     didst
    -0.59
     myſelf
    -0.59
    ConstraintMaker
    -0.58
     savages
    -0.58
     envers
    -0.58
    POSITIVE LOGITS
     mutual
    1.25
     Mutual
    1.09
    mutual
    1.02
    Mutual
    0.96
     Bureau
    0.84
     esternos
    0.72
    Bureau
    0.72
     mut
    0.67
     futures
    0.63
     aviation
    0.62
    Act Density 0.072%

    No Known Activations