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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wireType
    -0.57
    FailureListener
    -0.57
    ymce
    -0.56
    úsqueda
    -0.53
     sauvages
    -0.51
     يتيمه
    -0.50
    caring
    -0.50
     occurred
    -0.49
    ensaft
    -0.49
     Aktion
    -0.49
    POSITIVE LOGITS
     remember
    0.82
     remembers
    0.82
     thought
    0.74
     hadn
    0.73
     recalls
    0.72
    enumi
    0.70
     remembered
    0.70
    記得
    0.67
     knew
    0.67
     ingat
    0.66
    Act Density 0.288%

    No Known Activations