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

    Neuronpedia

    INDEX
    Explanations

    expressions of relationships and emotional dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.54
    expandindo
    -0.47
    setVerticalGroup
    -0.46
    -0.45
    -0.44
     ligiloj
    -0.43
    albero
    -0.42
     EconPapers
    -0.41
    homonymie
    -0.41
     penerima
    -0.41
    POSITIVE LOGITS
     themſelves
    0.78
     idol
    0.77
     ſtate
    0.73
     greateſt
    0.73
     Diſ
    0.72
     Chriftian
    0.72
     poffe
    0.71
     himſelf
    0.70
     ftate
    0.69
     Reſ
    0.69
    Act Density 0.116%

    No Known Activations