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

    Neuronpedia

    INDEX
    Explanations

    narratives and references related to relationships and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     générations
    -0.74
     habet
    -0.64
     quæ
    -0.62
     fidé
    -0.62
     mélang
    -0.59
     véritables
    -0.59
     varandra
    -0.59
     volonté
    -0.58
    tences
    -0.58
     revend
    -0.58
    POSITIVE LOGITS
     nog
    0.79
     digs
    0.77
     shenanigans
    0.76
     abode
    0.75
     wares
    0.74
     fella
    0.72
     ol
    0.71
     lil
    0.69
     critters
    0.69
     peeps
    0.69
    Act Density 0.504%

    No Known Activations