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

    Neuronpedia

    INDEX
    Explanations

    concepts that involve combining or merging different elements or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Egli
    -0.52
     InputDecoration
    -0.52
     Generale
    -0.52
    ymce
    -0.51
     confronti
    -0.49
     الدولى
    -0.49
     Kartoffeln
    -0.49
    biamo
    -0.49
     postIndex
    -0.48
     condam
    -0.47
    POSITIVE LOGITS
     combining
    0.80
     blending
    0.78
     combines
    0.74
    0.72
     blends
    0.72
     fusing
    0.71
    Combining
    0.70
     blend
    0.69
     Combining
    0.69
    LayoutStyle
    0.68
    Act Density 0.276%

    No Known Activations